diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..2e1fcfae01942d55f034e178d8d72d1280b266b8 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson|string }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{{ visible_text(m.content) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = ((content.split('')|first).rstrip('\n').split('')|last).lstrip('\n') %} + {%- set content = (content.split('')|last).lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson|string if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '\n' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e61f7a5f1553e967ed30f7da69d9a6cafef95a42 --- /dev/null +++ b/config.json @@ -0,0 +1,44 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 3, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1536, + "n_group": 1, + "n_routed_experts": 160, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 92, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151330, + "partial_rotary_factor": 0.5, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 2.5, + "tie_word_embeddings": false, + "topk_group": 1, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.1", + "unsloth_fixed": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4d49113f3e19072368c98e53180331c77c07c8a6 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "transformers_version": "4.54.0" +} diff --git a/model-00001-of-00093.safetensors b/model-00001-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..75f1b6e97dfe7ad82ea61d5f518227c67210f1b7 --- /dev/null +++ b/model-00001-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ec0ed85ee95cae5c9b76a7af7272a23169b81705c177c0212f65b24d4b8b41 +size 3753953568 diff --git a/model-00002-of-00093.safetensors b/model-00002-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b1512864b3c980c37563e814e522711da2684f0 --- /dev/null +++ b/model-00002-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5ed321e28aa0c3d31c1b9a9ac0e5666d915ffd89dff216a34427b33fb03c55 +size 650168352 diff --git a/model-00003-of-00093.safetensors b/model-00003-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..843bb355db02d9802d5b0f7e4eb9ad6e742aab06 --- /dev/null +++ b/model-00003-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c93996707aea7dc24a24e97eb72a57fbfd2d197a3cab970adf334ed28ae67abb +size 650168352 diff --git a/model-00004-of-00093.safetensors b/model-00004-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf985e19b0ae5be1daed5280fd001e43c5e9be2c --- /dev/null +++ b/model-00004-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c76581125a03a274386d8d0cd0e2c84242135bd0b728c33a3b311e1967b53ab7 +size 7871313120 diff --git a/model-00005-of-00093.safetensors b/model-00005-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7530cdf05fafccc4c5bb00682d02e05254c1891 --- /dev/null +++ b/model-00005-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cdb466003372faf78d647ffec247c33f0f2346177147ecce95e8e50b7b678a +size 7871313120 diff --git a/model-00006-of-00093.safetensors b/model-00006-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9cef97077b4b00a03ac3c1bc4dc5ed192c638f70 --- /dev/null +++ b/model-00006-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e643fc9c4b55c9861a965a744b85ae54453275d7a4dfdfad0ca7a9517ad18011 +size 7871313120 diff --git a/model-00007-of-00093.safetensors b/model-00007-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9862e0bbcf30d1259f39364a153872695ce3632c --- /dev/null +++ b/model-00007-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6145a87fc2f1e30123293802181b1c684ac710cdd6c929b2dab145154bbd9b7c +size 7871313120 diff --git a/model-00008-of-00093.safetensors b/model-00008-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea567cb8ba35efda9f051f64b8c74dc92bff8ae8 --- /dev/null +++ b/model-00008-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c5cfd2f82adabf3db579a5ff217506d0f5e1b7211492ef73b2209bb138f41f +size 7871313120 diff --git a/model-00009-of-00093.safetensors b/model-00009-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de3e50a01745507742c580f8e3833143c9eb3055 --- /dev/null +++ b/model-00009-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e37371e81407fd7b5cd543532c6bdca2bf865a2ee567e8f731777b19a9bd43 +size 7871313120 diff --git a/model-00010-of-00093.safetensors b/model-00010-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed7205db249d5edd241446b291f33c413de84b74 --- /dev/null +++ b/model-00010-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa2a54871e04125363468a6ca024de373ab38edb6f58b657913c2cd17ce5764 +size 7871313120 diff --git a/model-00011-of-00093.safetensors b/model-00011-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afba127cfc5fa225545f3d6817c7f48fd6944d46 --- /dev/null +++ b/model-00011-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049c06bc5a93318dcf91a7c60109c08e8df95a9a5130196a683434d9ede437f8 +size 7871313616 diff --git a/model-00012-of-00093.safetensors b/model-00012-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea57f87ea3674142e8f196a959aa9fafac84ff65 --- /dev/null +++ b/model-00012-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa88ebbabdc43302cf19ac2d81b27f2b16a3154fdd9ed096040615fa65013805 +size 7871313616 diff --git a/model-00013-of-00093.safetensors b/model-00013-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..212e32a4b555b63de9321eeb4aab550c3906c5fb --- /dev/null +++ b/model-00013-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a222612fd47c6ca8166275e66e723819baa3068eee2e1694f326066ac67ce4 +size 7871313616 diff --git a/model-00014-of-00093.safetensors b/model-00014-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0352a39beb5956ab88dc04ee2a4b350d8f16376 --- /dev/null +++ b/model-00014-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8d2da26be63fe9764a4a4cc6a00e58f406aeeda404c31b61612e5e74f9caf8 +size 7871313616 diff --git a/model-00015-of-00093.safetensors b/model-00015-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7912834f5881616c29121262816d32bdce07c9bc --- /dev/null +++ b/model-00015-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f832318ea861a4841a3ce0886eaa0ca7dee9729f74b5141634d7d7e9d6f2ba9 +size 7871313616 diff --git a/model-00016-of-00093.safetensors b/model-00016-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed8633530434b0dfc0790b109312d7ef79d6cc56 --- /dev/null +++ b/model-00016-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d344913210c96c6695341094e7da2817ccb94f3946ee9698a76eaaaaf60c1b44 +size 7871313616 diff --git a/model-00017-of-00093.safetensors b/model-00017-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eaa5780f4cee30ce7dd1574f018d7f19ee51b86c --- /dev/null +++ b/model-00017-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a4ce3054f3670fd5a7d1e71f502318e65ebb51ee629bd5eccd98adc736d4f6 +size 7871313616 diff --git a/model-00018-of-00093.safetensors b/model-00018-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1ee25ed3729a9c46872591efcaffa2474dfe6c1 --- /dev/null +++ b/model-00018-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006012f1bf7dd33271f12626000418c43e127b56bc70f3a5e314656ad717f424 +size 7871313616 diff --git a/model-00019-of-00093.safetensors b/model-00019-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19b177b0bcf161520bf39ea1deefe689dacb4bc8 --- /dev/null +++ b/model-00019-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:067349f582d85e7bd9b0326b82ee32cede246cf359b4e0b4c6cfe3f95caf8e21 +size 7871313616 diff --git a/model-00020-of-00093.safetensors b/model-00020-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5170766bdbadc2be7f81c7f94a23ab3a53f6bc8e --- /dev/null +++ b/model-00020-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21f395f920d50618e06b473f64971789746d86f3e20e2eab0483562ced51b2a +size 7871313616 diff --git a/model-00021-of-00093.safetensors b/model-00021-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f28bf98d8cf7bc315c4308c6f7734a32f60d5ee2 --- /dev/null +++ b/model-00021-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bde74ebffd96f550117c7b297198eadf75fb8c99603b6e78fd6d6bea62a8da8 +size 7871313616 diff --git a/model-00022-of-00093.safetensors b/model-00022-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..905fd725f440a65ff35c96e30627499edf1f2d0d --- /dev/null +++ b/model-00022-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9520583b0947a4bc9e3b22ee93dac2f19256f4f889ae17a5239e4275528db8 +size 7871313616 diff --git a/model-00023-of-00093.safetensors b/model-00023-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e66e4a9a9cc00dbd213d8183e387e3e292558be9 --- /dev/null +++ b/model-00023-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16613154e9ab024458f9acd079d7345db4a05593c5a596176640d68053665753 +size 7871313616 diff --git a/model-00024-of-00093.safetensors b/model-00024-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c320a483ff5425e09ad74118c9a79d501d44b640 --- /dev/null +++ b/model-00024-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b08d17d951a625b2cac46fcf15d7e4b6a99a28f91befabeb7d361fa7cac01e7b +size 7871313616 diff --git a/model-00025-of-00093.safetensors b/model-00025-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63d469acd7ed3a7f7a1ade71464989052f9f32e0 --- /dev/null +++ b/model-00025-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5cbe90ff83f0b2b91c92d5ba2e100263e8306ce3f6381bdd54051a6a8b6c3d +size 7871313616 diff --git a/model-00026-of-00093.safetensors b/model-00026-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14dd7546b2e1243f559a3e02623bb0cd9462631b --- /dev/null +++ b/model-00026-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea400d62257ef3f0412c8496c955a9ec7052fa4761dfbf4b35905aa04e73318 +size 7871313616 diff --git a/model-00027-of-00093.safetensors b/model-00027-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db58c2fcb5ec9cc8b8746d0e909cc12357c4b6d8 --- /dev/null +++ b/model-00027-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012d00adf402e18bb9a900d5dc549c2c45f047eb486ef2a44517a8e532dd9f2b +size 7871313616 diff --git a/model-00028-of-00093.safetensors b/model-00028-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d038150ce34403057264b8cd46048ad1ecbfc182 --- /dev/null +++ b/model-00028-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63de598020c34be07e77fb82319760bd539da4adfc48eecf83f64cc85ac35196 +size 7871313616 diff --git a/model-00029-of-00093.safetensors b/model-00029-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14f40a33a1202d0f6876eb69546f31b0d531ad60 --- /dev/null +++ b/model-00029-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ebe5474925c2edf5dea140224c9d506147f44c5accded8a854edb7538e88d3a +size 7871313616 diff --git a/model-00030-of-00093.safetensors b/model-00030-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bfc8656924535a5650e1cf0f786174c22693849 --- /dev/null +++ b/model-00030-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272627d9996b600a934e39c285914c04949e9e9ecbde8ddc2cdc228af5a0be42 +size 7871313616 diff --git a/model-00031-of-00093.safetensors b/model-00031-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55a18f5cb63871ce65192ceb23d31a25daaf3986 --- /dev/null +++ b/model-00031-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b8a452aa3db68fa81daa96d04af6b68aaaf2d9565e2b65ce427fbf821d6573 +size 7871313616 diff --git a/model-00032-of-00093.safetensors b/model-00032-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06467999332f890e254a17a7d8eebae698ed7bdf --- /dev/null +++ b/model-00032-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bc051e0ed087b3bcfaba48ecc5a2dab369ec95d0bc43b779daec146b9ab45b +size 7871313616 diff --git a/model-00033-of-00093.safetensors b/model-00033-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af7e85529f6dfa7f3c9660d2e7db46301d7c747c --- /dev/null +++ b/model-00033-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d506e1a1ac6faea9b46ece2be12d1d83d3e6987d8c836b0deebdb77a96baeac0 +size 7871313616 diff --git a/model-00034-of-00093.safetensors b/model-00034-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2a441d17ad450956a3b2c804c3e5bfbc48f6a37 --- /dev/null +++ b/model-00034-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b67f3dfb65d866d6dadeb3b33709641bdf93b34e5cd50ab480f08ca2fe1ab2 +size 7871313616 diff --git a/model-00035-of-00093.safetensors b/model-00035-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f3829c144f36ba6905cc0ae94a834e664be7fa59 --- /dev/null +++ b/model-00035-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab5187967ed92ebd28040749a6735e6dc5b5b7a921f26ecc320db909b1af3fab +size 7871313616 diff --git a/model-00036-of-00093.safetensors b/model-00036-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf72b205efdec3e0ac69c6b006ce6438384b1247 --- /dev/null +++ b/model-00036-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5babc5b903c4e8f30a014d6f63fe679331776eb8e19e1807099604085e506349 +size 7871313616 diff --git a/model-00037-of-00093.safetensors b/model-00037-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69a63e4dacf8b036fc0100b1af9124c6690eb4c5 --- /dev/null +++ b/model-00037-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8696f7e938ddd6a8a578467302b58907106add63ec9d06ada3f58db1e1f35b8a +size 7871313616 diff --git a/model-00038-of-00093.safetensors b/model-00038-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f4b6e4c4d5ac4714eacffd2bf2fe76f7dedda00e --- /dev/null +++ b/model-00038-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71ad1eda9008b3cca972e8c7637aba3bf598daba0f5f7146fcf70656d6807291 +size 7871313616 diff --git a/model-00039-of-00093.safetensors b/model-00039-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e00807ac88e857b087c0166f11f028347860a67 --- /dev/null +++ b/model-00039-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc174288c0a6dfe1ed30e7b9d0b14b4008cef1c44121ecba5d3fc5711f9ffcf +size 7871313616 diff --git a/model-00040-of-00093.safetensors b/model-00040-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85b750b876db13425864c974e1f447260d6d4eb3 --- /dev/null +++ b/model-00040-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33bc1f191e6ece41ac959fae053e56c8d9b7aae4e248396db308df192b0dfdca +size 7871313616 diff --git a/model-00041-of-00093.safetensors b/model-00041-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e8045d9c088fb44d0cc73559d8dc39e9d3fd23e --- /dev/null +++ b/model-00041-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1086567592913cf955a099e6bd36d69803197a5e737895e82d27e139ee797454 +size 7871313616 diff --git a/model-00042-of-00093.safetensors b/model-00042-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd5080274bb57b6f9605aa56a40c23a4ac15be9d --- /dev/null +++ b/model-00042-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd01aed8bd9f3875c999a912c10806379df34083c8d5ea86dbeed586218404e5 +size 7871313616 diff --git a/model-00043-of-00093.safetensors b/model-00043-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2921a94700a4dc1e07d0588acaffb8b6a597ddff --- /dev/null +++ b/model-00043-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3757974e615f565fb9179ca721617f92c1c46e02cb27de2173ccf69851a4bbe5 +size 7871313616 diff --git a/model-00044-of-00093.safetensors b/model-00044-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34699341841889eeaf4c7e73bb73576df2efc657 --- /dev/null +++ b/model-00044-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:333883124d4baa2d0ad5527832875418c574a9bb9d022184573d73da6b0450bb +size 7871313616 diff --git a/model-00045-of-00093.safetensors b/model-00045-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..734cb8c87c063849794098f867f0ebe465b225d9 --- /dev/null +++ b/model-00045-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2347fda76deadd548681a1b96d6868eed8c00a37808ece8ff71011a54989c091 +size 7871313616 diff --git a/model-00046-of-00093.safetensors b/model-00046-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4a0dcc0d936b260329f026453ea571719fd1e7d --- /dev/null +++ b/model-00046-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be1386859ce861008c1f5333277a91e9b76dd522f4316edc25d5bf48e18934b +size 7871313616 diff --git a/model-00047-of-00093.safetensors b/model-00047-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8684adce944ec955a0bc41f751ea1c6f6619205 --- /dev/null +++ b/model-00047-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:761cf240ce8a79b8ccdf573b6726702b78dd528e40649a87fbf8f780369ee14b +size 7871313616 diff --git a/model-00048-of-00093.safetensors b/model-00048-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8758eced35e25b8c7aa3f3a765971b8d2670f96 --- /dev/null +++ b/model-00048-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754ae933c03a3c88bf4f46b2c2c74ca0340cec635a1b37a6dabc19639aef4573 +size 7871313616 diff --git a/model-00049-of-00093.safetensors b/model-00049-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5097e5ca39f4b350d84337d0899c728be00f4940 --- /dev/null +++ b/model-00049-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d536c990566070af88255c2f012488e52e923ab463ee24163408e3e39bed56 +size 7871313616 diff --git a/model-00050-of-00093.safetensors b/model-00050-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f3640aec94767e8e487dd42e2d3a19b56865a44 --- /dev/null +++ b/model-00050-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5def8db9af1162a0af3532726fb9c51b4a715107d23fc3b1c7a533ace8b526d8 +size 7871313616 diff --git a/model-00051-of-00093.safetensors b/model-00051-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a63074e8ca3982743a5dae1d5cef8f662056312e --- /dev/null +++ b/model-00051-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5cb2a9255ede6cf9b4bb3481e9a68207c51af273121c72950c0719b00b6adb5 +size 7871313616 diff --git a/model-00052-of-00093.safetensors b/model-00052-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cdc61795e9a6244a75b5fd9238be5a82330c7d5 --- /dev/null +++ b/model-00052-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477e80817f20318d75644a9e6ee259dfa3397b61dcf3002fd3d88bff4f96067b +size 7871313616 diff --git a/model-00053-of-00093.safetensors b/model-00053-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7b6cd2f27eae06e46ea0b931a0444a8b86a4ee4 --- /dev/null +++ b/model-00053-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09236431661fff9166dbe839dafd37e3f9c1da9553abc15510f7a347071ec6b4 +size 7871313616 diff --git a/model-00054-of-00093.safetensors b/model-00054-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86a3b22f094cc3bb94410c9a1f00d79c99cb81ee --- /dev/null +++ b/model-00054-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e3b985addf4664e9e4c06c5ea70ed9560572712d35fea72f84f56291cda876 +size 7871313616 diff --git a/model-00055-of-00093.safetensors b/model-00055-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9317b62c724c7eb76fbd722943129405602c40dc --- /dev/null +++ b/model-00055-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4f7443ab946e1909729f0b89172219a51d517228278bcd64dce3ac91ecd7f6 +size 7871313616 diff --git a/model-00056-of-00093.safetensors b/model-00056-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..274ea48431eb733bc1ebdf5c867ccbf60d371672 --- /dev/null +++ b/model-00056-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4922b01ec5a8ff7b0b396793ec1469758bd6a8f764addf9de78b0ea6028c83fe +size 7871313616 diff --git a/model-00057-of-00093.safetensors b/model-00057-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dfcd408d5fd0154168b8a6c29674b85360fe120b --- /dev/null +++ b/model-00057-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f208efecaead3e9e64c6e60c881d81d04db6f30c482497bd854500cef0e48e6d +size 7871313616 diff --git a/model-00058-of-00093.safetensors b/model-00058-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b357f87c0480ccefb46803acada81ed9aec04c38 --- /dev/null +++ b/model-00058-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ffbaa56d5f0f395c43869fec71e221f8be5448b900ef7450477521a8c26186 +size 7871313616 diff --git a/model-00059-of-00093.safetensors b/model-00059-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed857501c39d28eb7d826753f1e99b031d694fcd --- /dev/null +++ b/model-00059-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981536347ae1d20f852e98639ee4fe7f2d4f6c20b4c9c8ab86983b81480fa79f +size 7871313616 diff --git a/model-00060-of-00093.safetensors b/model-00060-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..601ba3034fc149ab4bdbc937f1ae657276975938 --- /dev/null +++ b/model-00060-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cb54647de5b032d78539c298887bb350f5d0eef95b01b1f85dafc7d90ab89f7 +size 7871313616 diff --git a/model-00061-of-00093.safetensors b/model-00061-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..541104f807d0ff3261c372566ad8c6f167c5737c --- /dev/null +++ b/model-00061-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a25bdf49e05d70ed871eb422ef964ce6bb7c7976224e5c981eca4d823a7450a +size 7871313616 diff --git a/model-00062-of-00093.safetensors b/model-00062-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1e4044cbafa006d32dc2ac83a6701442bc82050 --- /dev/null +++ b/model-00062-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6193ade7e5ce6068b1d68128a3f7d6034e7c0a00096ae634b79495938cb57f78 +size 7871313616 diff --git a/model-00063-of-00093.safetensors b/model-00063-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb15d8702212d4c6ee4597af8c60098a2ce45cee --- /dev/null +++ b/model-00063-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ea79604320c3a63a92aaea99feb087abb71cd143b4d6d866714bf2b88e6787 +size 7871313616 diff --git a/model-00064-of-00093.safetensors b/model-00064-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ddc1e82119330338b24724aec68f1d0135da76b --- /dev/null +++ b/model-00064-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f5c79df17581a2a053989e9a68b2721edab10317220224e6a4bae0d4b685c34 +size 7871313616 diff --git a/model-00065-of-00093.safetensors b/model-00065-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6683d004327fb8c0576af124e29aa6bc4f34be93 --- /dev/null +++ b/model-00065-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d0bc11f2cb4e27795af3c991d41806a0ba193136b260732cc6e0575a672f21 +size 7871313616 diff --git a/model-00066-of-00093.safetensors b/model-00066-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..019a609eef99db00403ed73bd216aab281201bae --- /dev/null +++ b/model-00066-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0141817eb441c5e6482ad652124b6bf57eff5bffd482af6b462a0659fd81bf1c +size 7871313616 diff --git a/model-00067-of-00093.safetensors b/model-00067-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9dcff6bea2031398bf1a3cb41fe0ad76defd19a8 --- /dev/null +++ b/model-00067-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef13cf68794ccf7f480af779f663cbfc035f1969cb0c3b2c405c157ab4a11263 +size 7871313616 diff --git a/model-00068-of-00093.safetensors b/model-00068-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86b040faec235e1ee2d46ccb06860fde025a5f4b --- /dev/null +++ b/model-00068-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96e70e883199f7b9a405d7b3779f1d7f042456b8d4fb87a49b60dc9917b7159 +size 7871313616 diff --git a/model-00069-of-00093.safetensors b/model-00069-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef707509c8c4b470335e812c87ad5c4e64670ab9 --- /dev/null +++ b/model-00069-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f780af0c2585122e56bbdd92b67bc4533a71e4d7ccb72b6c3077086540a1ef +size 7871313616 diff --git a/model-00070-of-00093.safetensors b/model-00070-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1abdcb51c7cb74315b451aee6e5380bbcd45d17a --- /dev/null +++ b/model-00070-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea43fb7dd55a9f9c545f39b893fa2cc5daaa3c21261a2f07ccf0294380f9171a +size 7871313616 diff --git a/model-00071-of-00093.safetensors b/model-00071-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32a98a481e4dbffe7ec22a26794d91d07c29055e --- /dev/null +++ b/model-00071-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af29faa01ab52323979c6edf481a66e729d84bc394166f1e7dd06e5e4c3e3aad +size 7871313616 diff --git a/model-00072-of-00093.safetensors b/model-00072-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1d9ea9c83b48fad2008f13933da5a27bd1277d7 --- /dev/null +++ b/model-00072-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052b73b892921c90c6c167e0545f139360fccead36f495a086fc3b7a38eaeacb +size 7871313616 diff --git a/model-00073-of-00093.safetensors b/model-00073-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9521df88c37f468fcf61b561a9f11b5b069e06de --- /dev/null +++ b/model-00073-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b719c8a1b401dcb2bc1e7932ae120306004ca9fd8a831f1a09f545112db3e6 +size 7871313616 diff --git a/model-00074-of-00093.safetensors b/model-00074-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c1a8a28dd154eaaa392d6b58646e5408d03f5d2 --- /dev/null +++ b/model-00074-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b5b2357cd1140e923c0940edce64a728da3ad9a95a295734ef6d134dd86ee30 +size 7871313616 diff --git a/model-00075-of-00093.safetensors b/model-00075-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5fba7a072c2161e958272495315c0c3637b8fd5 --- /dev/null +++ b/model-00075-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06347eff2172048d92c92d1ac6f2ef73724fe3f9e2a680a6d2528d558abd8f54 +size 7871313616 diff --git a/model-00076-of-00093.safetensors b/model-00076-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c7ee18bb409320dfc58517fc9c604456445f23e --- /dev/null +++ b/model-00076-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92139d1549083249c060eb7df2cfab7eabc4b48df7740cfb6da6ca01f2fab07b +size 7871313616 diff --git a/model-00077-of-00093.safetensors b/model-00077-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..089be4a23bd0e04c02019edab557ab084a043c00 --- /dev/null +++ b/model-00077-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83de3668f05405afb76e9fd38b463e838bee6c923082932f9b233c1e2999a5d +size 7871313616 diff --git a/model-00078-of-00093.safetensors b/model-00078-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..31546aed134c8ee5788d0b2c12595f9ecd049bd3 --- /dev/null +++ b/model-00078-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e38039f00abf6b589910ce53c3b6f289b76da58d7c1116ca7f2f5761a725970 +size 7871313616 diff --git a/model-00079-of-00093.safetensors b/model-00079-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..079466e730bd2a2812a45708cbe497abc9bfe758 --- /dev/null +++ b/model-00079-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb662c03ea9100602610460cda218aaaf8c211a9eb7946b4f1ce1bd8b88f336 +size 7871313616 diff --git a/model-00080-of-00093.safetensors b/model-00080-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef7067b177226c0f36ccd16c0b8f31faffd0bdcd --- /dev/null +++ b/model-00080-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ded1950bb973b5602e883c88a236079b26355c8e7eeae73cca44f597653096 +size 7871313616 diff --git a/model-00081-of-00093.safetensors b/model-00081-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc5a4e7f1348a18da076e1ba6f7a32b5f2a82eac --- /dev/null +++ b/model-00081-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1888c4eddb11e3fb152dc0cfc4eaf2e3473fcd79bcf412468b3c1f68b06e95c6 +size 7871313616 diff --git a/model-00082-of-00093.safetensors b/model-00082-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..631a0d9b0f0c4b9fba59f46cbcd2d46494eb78c1 --- /dev/null +++ b/model-00082-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e540a950da1d7bcceb4a6a42c256132857b365e8db32ecda48f778996bec5a0 +size 7871313616 diff --git a/model-00083-of-00093.safetensors b/model-00083-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be743a70ee6e37aed83277a92a9d0c893d968ed8 --- /dev/null +++ b/model-00083-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a732c84b796ac322f71887e554418c71293a6953acd55b974f53102ab8dee88b +size 7871313616 diff --git a/model-00084-of-00093.safetensors b/model-00084-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..545dc73bd9dc1792db11839e79963b2774c38c71 --- /dev/null +++ b/model-00084-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2104534f965d287f4e7a0caa1e5f87367c5300377b9e5655c09349218efc1a +size 7871313616 diff --git a/model-00085-of-00093.safetensors b/model-00085-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7393bdf84a2c22a92c3dea6a55e0312826196bb8 --- /dev/null +++ b/model-00085-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b26a54b7927c94a51cdd714381df95dba4a548c89c258185e22b438747d9b1 +size 7871313616 diff --git a/model-00086-of-00093.safetensors b/model-00086-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2547bd10ebb02b836d21ad91b8facdce8ff820a7 --- /dev/null +++ b/model-00086-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb4167f124db49fe33bf5f23b88284142c1c04a1b3220f2d9ee7a2ee80e67df +size 7871313616 diff --git a/model-00087-of-00093.safetensors b/model-00087-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e28477578020ee75150f609babe38a187c0e17c2 --- /dev/null +++ b/model-00087-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f78f3de2c13a7e5bfdb963008ef4cf179a1dd6a15d1721454d441b3acc06d6 +size 7871313616 diff --git a/model-00088-of-00093.safetensors b/model-00088-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80208e92d5ce776f73a0d6198e7a7dc020b7d985 --- /dev/null +++ b/model-00088-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1599e223edbbbdc03a2987665d636c53c12df5d798cbade1bd4cc1ce36bb6b +size 7871313616 diff --git a/model-00089-of-00093.safetensors b/model-00089-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2b480b125408da684f9f4b1a2fb05cd4207eb24 --- /dev/null +++ b/model-00089-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c14a81092ddd8567b8e1f6083c6e89b16a819b528ec0f0eb8c0404e9f1ada4 +size 7871313616 diff --git a/model-00090-of-00093.safetensors b/model-00090-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7206a97b578174308e2b2872799135da6259db5e --- /dev/null +++ b/model-00090-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88df60618ac4aa6b334f173947ca911f3f91d7ff104c4acd94bc3b266ec249d6 +size 7871313616 diff --git a/model-00091-of-00093.safetensors b/model-00091-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..701a3a9a97cf7ebeb87a112ead0d0ff19885437c --- /dev/null +++ b/model-00091-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4498be3e0e216922f10185d2aa3376a6f1562f3f22b53d6dd5c9ceeed658d3e4 +size 7871313616 diff --git a/model-00092-of-00093.safetensors b/model-00092-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01f5c74915850c2ff9b87d80818057ded57056cd --- /dev/null +++ b/model-00092-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1747f9cb14ce71b4744855b59ecdfbe0ce9e43315cb95d43a5e5d601abe3dcb1 +size 10975109272 diff --git a/model-00093-of-00093.safetensors b/model-00093-of-00093.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a17dfd2670b9f352f276c77ca6b03517b1cc3a7 --- /dev/null +++ b/model-00093-of-00093.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084c2cfc3045f744439c646e0470bf8b8ebcc6404e0ede1642efb25b0fbe9c3b +size 7976202392 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b65b74c7f9a0e8d0477c5cf345c4eb6ae707b16a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,44698 @@ +{ + "metadata": { + "total_size": 358337791296 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00093.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00093.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00093.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00093.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00093.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00093.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00093.safetensors", + "model.layers.92.embed_tokens.weight": "model-00001-of-00093.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00093.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00093.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00093.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00093.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00093.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00093.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00093.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00093.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00093.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00093.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00093.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00093.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.128.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.128.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.128.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.129.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.129.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.129.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.130.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.130.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.130.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.131.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.131.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.131.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.132.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.132.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.132.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.133.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.133.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.133.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.134.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.134.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.134.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.135.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.135.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.135.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.136.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.136.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.136.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.137.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.137.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.137.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.138.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.138.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.138.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.139.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.139.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.139.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.140.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.140.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.140.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.141.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.141.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.141.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.142.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.142.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.142.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.143.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.143.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.143.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.144.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.144.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.144.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.145.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.145.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.145.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.146.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.146.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.146.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.147.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.147.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.147.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.148.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.148.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.148.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.149.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.149.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.149.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.150.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.150.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.150.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.151.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.151.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.151.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.152.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.152.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.152.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.153.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.153.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.153.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.154.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.154.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.154.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.155.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.155.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.155.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.156.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.156.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.156.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.157.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.157.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.157.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.158.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.158.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.158.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.159.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.159.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.159.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00093.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00093.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.128.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.128.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.128.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.129.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.129.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.129.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.130.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.130.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.130.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.131.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.131.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.131.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.132.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.132.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.132.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.133.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.133.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.133.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.134.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.134.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.134.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.135.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.135.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.135.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.136.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.136.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.136.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.137.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.137.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.137.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.138.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.138.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.138.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.139.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.139.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.139.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.140.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.140.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.140.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.141.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.141.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.141.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.142.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.142.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.142.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.143.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.143.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.143.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.144.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.144.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.144.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.145.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.145.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.145.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.146.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.146.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.146.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.147.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.147.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.147.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.148.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.148.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.148.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.149.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.149.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.149.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.150.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.150.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.150.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.151.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.151.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.151.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.152.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.152.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.152.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.153.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.153.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.153.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.154.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.154.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.154.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.155.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.155.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.155.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.156.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.156.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.156.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.157.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.157.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.157.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.158.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.158.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.158.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.159.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.159.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.159.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00093.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00093.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.128.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.128.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.128.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.129.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.129.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.129.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.130.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.130.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.130.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.131.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.131.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.131.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.132.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.132.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.132.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.133.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.133.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.133.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.134.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.134.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.134.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.135.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.135.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.135.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.136.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.136.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.136.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.137.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.137.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.137.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.138.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.138.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.138.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.139.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.139.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.139.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.140.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.140.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.140.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.141.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.141.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.141.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.142.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.142.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.142.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.143.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.143.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.143.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.144.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.144.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.144.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.145.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.145.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.145.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.146.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.146.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.146.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.147.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.147.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.147.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.148.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.148.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.148.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.149.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.149.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.149.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.150.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.150.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.150.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.151.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.151.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.151.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.152.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.152.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.152.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.153.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.153.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.153.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.154.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.154.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.154.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.155.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.155.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.155.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.156.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.156.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.156.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.157.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.157.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.157.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.158.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.158.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.158.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.159.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.159.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.159.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00093.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00093.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.128.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.128.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.128.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.129.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.129.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.129.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.130.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.130.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.130.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.131.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.131.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.131.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.132.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.132.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.132.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.133.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.133.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.133.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.134.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.134.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.134.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.135.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.135.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.135.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.136.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.136.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.136.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.137.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.137.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.137.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.138.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.138.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.138.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.139.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.139.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.139.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.140.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.140.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.140.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.141.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.141.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.141.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.142.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.142.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.142.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.143.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.143.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.143.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.144.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.144.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.144.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.145.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.145.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.145.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.146.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.146.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.146.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.147.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.147.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.147.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.148.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.148.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.148.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.149.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.149.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.149.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.150.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.150.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.150.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.151.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.151.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.151.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.152.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.152.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.152.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.153.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.153.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.153.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.154.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.154.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.154.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.155.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.155.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.155.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.156.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.156.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.156.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.157.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.157.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.157.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.158.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.158.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.158.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.159.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.159.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.159.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00093.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00093.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.128.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.128.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.128.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.129.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.129.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.129.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.130.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.130.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.130.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.131.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.131.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.131.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.132.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.132.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.132.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.133.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.133.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.133.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.134.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.134.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.134.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.135.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.135.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.135.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.136.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.136.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.136.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.137.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.137.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.137.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.138.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.138.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.138.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.139.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.139.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.139.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.140.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.140.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.140.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.141.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.141.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.141.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.142.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.142.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.142.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.143.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.143.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.143.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.144.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.144.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.144.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.145.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.145.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.145.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.146.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.146.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.146.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.147.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.147.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.147.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.148.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.148.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.148.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.149.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.149.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.149.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.150.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.150.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.150.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.151.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.151.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.151.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.152.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.152.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.152.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.153.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.153.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.153.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.154.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.154.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.154.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.155.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.155.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.155.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.156.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.156.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.156.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.157.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.157.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.157.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.158.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.158.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.158.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.159.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.159.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.159.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00093.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00093.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.128.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.128.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.128.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.129.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.129.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.129.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.130.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.130.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.130.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.131.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.131.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.131.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.132.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.132.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.132.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.133.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.133.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.133.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.134.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.134.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.134.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.135.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.135.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.135.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.136.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.136.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.136.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.137.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.137.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.137.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.138.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.138.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.138.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.139.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.139.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.139.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.140.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.140.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.140.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.141.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.141.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.141.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.142.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.142.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.142.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.143.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.143.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.143.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.144.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.144.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.144.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.145.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.145.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.145.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.146.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.146.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.146.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.147.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.147.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.147.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.148.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.148.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.148.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.149.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.149.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.149.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.150.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.150.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.150.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.151.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.151.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.151.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.152.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.152.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.152.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.153.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.153.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.153.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.154.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.154.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.154.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.155.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.155.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.155.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.156.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.156.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.156.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.157.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.157.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.157.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.158.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.158.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.158.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.159.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.159.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.159.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00093.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00093.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.128.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.128.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.128.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.129.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.129.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.129.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.130.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.130.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.130.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.131.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.131.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.131.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.132.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.132.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.132.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.133.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.133.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.133.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.134.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.134.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.134.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.135.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.135.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.135.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.136.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.136.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.136.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.137.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.137.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.137.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.138.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.138.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.138.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.139.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.139.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.139.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.140.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.140.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.140.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.141.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.141.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.141.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.142.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.142.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.142.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.143.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.143.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.143.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.144.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.144.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.144.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.145.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.145.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.145.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.146.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.146.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.146.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.147.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.147.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.147.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.148.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.148.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.148.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.149.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.149.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.149.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.150.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.150.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.150.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.151.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.151.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.151.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.152.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.152.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.152.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.153.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.153.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.153.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.154.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.154.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.154.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.155.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.155.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.155.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.156.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.156.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.156.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.157.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.157.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.157.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.158.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.158.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.158.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.159.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.159.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.159.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00093.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00093.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.128.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.128.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.128.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.129.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.129.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.129.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.130.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.130.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.130.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.131.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.131.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.131.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.132.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.132.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.132.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.133.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.133.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.133.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.134.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.134.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.134.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.135.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.135.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.135.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.136.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.136.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.136.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.137.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.137.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.137.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.138.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.138.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.138.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.139.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.139.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.139.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.140.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.140.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.140.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.141.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.141.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.141.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.142.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.142.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.142.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.143.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.143.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.143.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.144.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.144.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.144.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.145.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.145.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.145.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.146.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.146.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.146.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.147.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.147.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.147.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.148.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.148.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.148.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.149.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.149.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.149.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.150.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.150.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.150.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.151.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.151.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.151.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.152.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.152.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.152.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.153.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.153.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.153.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.154.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.154.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.154.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.155.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.155.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.155.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.156.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.156.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.156.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.157.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.157.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.157.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.158.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.158.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.158.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.159.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.159.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.159.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00011-of-00093.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00093.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.128.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.128.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.128.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.129.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.129.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.129.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.130.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.130.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.130.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.131.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.131.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.131.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.132.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.132.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.132.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.133.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.133.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.133.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.134.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.134.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.134.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.135.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.135.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.135.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.136.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.136.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.136.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.137.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.137.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.137.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.138.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.138.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.138.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.139.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.139.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.139.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.140.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.140.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.140.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.141.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.141.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.141.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.142.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.142.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.142.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.143.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.143.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.143.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.144.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.144.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.144.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.145.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.145.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.145.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.146.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.146.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.146.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.147.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.147.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.147.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.148.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.148.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.148.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.149.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.149.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.149.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.150.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.150.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.150.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.151.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.151.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.151.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.152.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.152.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.152.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.153.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.153.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.153.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.154.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.154.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.154.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.155.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.155.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.155.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.156.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.156.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.156.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.157.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.157.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.157.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.158.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.158.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.158.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.159.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.159.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.159.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00012-of-00093.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00093.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.128.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.128.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.128.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.129.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.129.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.129.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.130.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.130.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.130.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.131.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.131.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.131.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.132.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.132.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.132.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.133.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.133.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.133.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.134.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.134.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.134.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.135.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.135.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.135.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.136.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.136.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.136.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.137.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.137.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.137.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.138.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.138.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.138.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.139.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.139.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.139.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.140.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.140.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.140.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.141.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.141.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.141.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.142.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.142.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.142.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.143.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.143.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.143.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.144.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.144.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.144.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.145.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.145.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.145.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.146.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.146.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.146.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.147.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.147.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.147.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.148.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.148.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.148.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.149.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.149.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.149.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.150.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.150.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.150.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.151.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.151.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.151.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.152.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.152.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.152.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.153.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.153.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.153.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.154.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.154.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.154.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.155.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.155.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.155.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.156.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.156.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.156.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.157.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.157.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.157.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.158.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.158.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.158.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.159.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.159.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.159.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00013-of-00093.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00093.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.128.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.128.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.128.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.129.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.129.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.129.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.130.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.130.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.130.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.131.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.131.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.131.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.132.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.132.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.132.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.133.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.133.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.133.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.134.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.134.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.134.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.135.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.135.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.135.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.136.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.136.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.136.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.137.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.137.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.137.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.138.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.138.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.138.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.139.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.139.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.139.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.140.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.140.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.140.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.141.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.141.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.141.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.142.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.142.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.142.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.143.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.143.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.143.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.144.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.144.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.144.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.145.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.145.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.145.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.146.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.146.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.146.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.147.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.147.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.147.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.148.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.148.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.148.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.149.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.149.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.149.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.150.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.150.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.150.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.151.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.151.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.151.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.152.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.152.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.152.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.153.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.153.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.153.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.154.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.154.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.154.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.155.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.155.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.155.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.156.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.156.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.156.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.157.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.157.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.157.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.158.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.158.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.158.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.159.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.159.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.159.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00014-of-00093.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00093.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.128.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.128.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.128.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.129.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.129.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.129.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.130.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.130.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.130.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.131.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.131.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.131.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.132.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.132.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.132.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.133.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.133.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.133.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.134.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.134.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.134.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.135.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.135.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.135.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.136.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.136.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.136.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.137.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.137.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.137.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.138.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.138.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.138.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.139.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.139.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.139.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.140.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.140.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.140.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.141.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.141.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.141.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.142.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.142.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.142.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.143.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.143.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.143.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.144.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.144.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.144.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.145.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.145.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.145.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.146.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.146.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.146.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.147.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.147.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.147.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.148.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.148.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.148.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.149.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.149.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.149.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.150.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.150.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.150.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.151.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.151.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.151.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.152.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.152.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.152.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.153.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.153.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.153.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.154.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.154.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.154.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.155.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.155.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.155.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.156.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.156.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.156.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.157.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.157.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.157.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.158.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.158.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.158.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.159.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.159.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.159.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00015-of-00093.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00093.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.128.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.128.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.128.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.129.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.129.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.129.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.130.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.130.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.130.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.131.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.131.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.131.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.132.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.132.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.132.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.133.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.133.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.133.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.134.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.134.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.134.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.135.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.135.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.135.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.136.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.136.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.136.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.137.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.137.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.137.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.138.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.138.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.138.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.139.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.139.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.139.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.140.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.140.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.140.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.141.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.141.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.141.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.142.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.142.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.142.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.143.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.143.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.143.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.144.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.144.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.144.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.145.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.145.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.145.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.146.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.146.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.146.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.147.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.147.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.147.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.148.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.148.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.148.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.149.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.149.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.149.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.150.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.150.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.150.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.151.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.151.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.151.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.152.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.152.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.152.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.153.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.153.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.153.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.154.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.154.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.154.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.155.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.155.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.155.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.156.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.156.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.156.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.157.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.157.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.157.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.158.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.158.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.158.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.159.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.159.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.159.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00016-of-00093.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00093.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.128.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.128.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.128.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.129.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.129.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.129.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.130.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.130.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.130.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.131.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.131.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.131.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.132.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.132.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.132.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.133.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.133.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.133.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.134.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.134.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.134.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.135.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.135.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.135.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.136.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.136.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.136.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.137.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.137.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.137.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.138.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.138.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.138.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.139.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.139.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.139.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.140.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.140.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.140.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.141.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.141.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.141.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.142.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.142.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.142.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.143.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.143.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.143.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.144.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.144.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.144.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.145.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.145.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.145.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.146.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.146.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.146.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.147.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.147.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.147.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.148.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.148.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.148.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.149.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.149.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.149.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.150.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.150.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.150.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.151.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.151.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.151.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.152.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.152.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.152.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.153.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.153.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.153.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.154.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.154.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.154.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.155.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.155.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.155.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.156.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.156.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.156.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.157.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.157.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.157.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.158.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.158.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.158.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.159.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.159.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.159.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00017-of-00093.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00093.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.128.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.128.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.128.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.129.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.129.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.129.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.130.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.130.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.130.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.131.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.131.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.131.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.132.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.132.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.132.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.133.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.133.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.133.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.134.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.134.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.134.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.135.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.135.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.135.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.136.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.136.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.136.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.137.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.137.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.137.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.138.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.138.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.138.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.139.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.139.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.139.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.140.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.140.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.140.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.141.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.141.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.141.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.142.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.142.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.142.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.143.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.143.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.143.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.144.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.144.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.144.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.145.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.145.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.145.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.146.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.146.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.146.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.147.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.147.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.147.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.148.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.148.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.148.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.149.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.149.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.149.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.150.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.150.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.150.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.151.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.151.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.151.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.152.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.152.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.152.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.153.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.153.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.153.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.154.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.154.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.154.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.155.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.155.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.155.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.156.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.156.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.156.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.157.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.157.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.157.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.158.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.158.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.158.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.159.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.159.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.159.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00018-of-00093.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00093.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.128.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.128.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.128.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.129.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.129.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.129.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.130.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.130.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.130.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.131.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.131.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.131.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.132.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.132.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.132.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.133.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.133.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.133.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.134.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.134.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.134.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.135.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.135.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.135.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.136.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.136.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.136.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.137.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.137.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.137.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.138.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.138.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.138.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.139.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.139.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.139.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.140.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.140.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.140.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.141.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.141.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.141.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.142.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.142.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.142.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.143.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.143.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.143.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.144.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.144.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.144.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.145.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.145.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.145.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.146.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.146.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.146.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.147.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.147.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.147.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.148.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.148.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.148.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.149.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.149.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.149.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.150.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.150.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.150.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.151.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.151.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.151.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.152.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.152.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.152.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.153.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.153.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.153.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.154.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.154.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.154.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.155.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.155.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.155.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.156.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.156.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.156.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.157.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.157.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.157.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.158.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.158.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.158.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.159.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.159.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.159.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00019-of-00093.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00093.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.128.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.128.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.128.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.129.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.129.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.129.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.130.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.130.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.130.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.131.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.131.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.131.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.132.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.132.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.132.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.133.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.133.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.133.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.134.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.134.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.134.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.135.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.135.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.135.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.136.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.136.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.136.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.137.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.137.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.137.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.138.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.138.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.138.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.139.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.139.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.139.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.140.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.140.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.140.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.141.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.141.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.141.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.142.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.142.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.142.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.143.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.143.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.143.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.144.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.144.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.144.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.145.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.145.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.145.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.146.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.146.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.146.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.147.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.147.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.147.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.148.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.148.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.148.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.149.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.149.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.149.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.150.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.150.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.150.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.151.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.151.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.151.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.152.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.152.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.152.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.153.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.153.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.153.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.154.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.154.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.154.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.155.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.155.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.155.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.156.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.156.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.156.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.157.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.157.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.157.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.158.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.158.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.158.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.159.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.159.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.159.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00020-of-00093.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00093.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.128.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.128.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.128.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.129.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.129.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.129.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.130.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.130.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.130.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.131.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.131.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.131.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.132.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.132.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.132.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.133.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.133.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.133.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.134.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.134.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.134.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.135.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.135.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.135.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.136.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.136.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.136.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.137.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.137.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.137.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.138.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.138.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.138.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.139.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.139.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.139.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.140.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.140.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.140.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.141.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.141.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.141.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.142.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.142.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.142.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.143.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.143.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.143.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.144.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.144.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.144.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.145.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.145.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.145.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.146.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.146.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.146.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.147.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.147.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.147.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.148.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.148.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.148.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.149.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.149.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.149.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.150.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.150.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.150.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.151.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.151.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.151.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.152.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.152.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.152.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.153.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.153.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.153.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.154.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.154.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.154.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.155.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.155.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.155.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.156.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.156.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.156.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.157.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.157.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.157.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.158.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.158.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.158.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.159.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.159.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.159.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00021-of-00093.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00093.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.128.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.128.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.128.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.129.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.129.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.129.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.130.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.130.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.130.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.131.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.131.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.131.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.132.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.132.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.132.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.133.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.133.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.133.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.134.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.134.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.134.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.135.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.135.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.135.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.136.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.136.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.136.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.137.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.137.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.137.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.138.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.138.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.138.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.139.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.139.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.139.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.140.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.140.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.140.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.141.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.141.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.141.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.142.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.142.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.142.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.143.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.143.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.143.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.144.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.144.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.144.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.145.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.145.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.145.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.146.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.146.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.146.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.147.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.147.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.147.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.148.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.148.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.148.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.149.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.149.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.149.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.150.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.150.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.150.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.151.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.151.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.151.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.152.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.152.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.152.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.153.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.153.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.153.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.154.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.154.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.154.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.155.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.155.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.155.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.156.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.156.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.156.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.157.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.157.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.157.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.158.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.158.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.158.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.159.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.159.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.159.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00022-of-00093.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00093.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.128.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.128.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.128.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.129.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.129.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.129.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.130.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.130.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.130.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.131.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.131.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.131.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.132.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.132.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.132.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.133.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.133.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.133.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.134.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.134.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.134.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.135.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.135.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.135.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.136.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.136.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.136.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.137.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.137.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.137.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.138.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.138.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.138.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.139.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.139.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.139.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.140.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.140.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.140.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.141.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.141.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.141.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.142.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.142.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.142.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.143.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.143.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.143.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.144.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.144.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.144.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.145.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.145.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.145.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.146.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.146.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.146.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.147.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.147.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.147.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.148.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.148.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.148.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.149.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.149.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.149.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.150.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.150.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.150.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.151.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.151.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.151.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.152.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.152.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.152.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.153.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.153.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.153.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.154.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.154.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.154.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.155.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.155.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.155.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.156.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.156.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.156.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.157.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.157.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.157.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.158.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.158.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.158.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.159.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.159.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.159.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00023-of-00093.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00093.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.128.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.128.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.128.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.129.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.129.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.129.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.130.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.130.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.130.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.131.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.131.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.131.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.132.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.132.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.132.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.133.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.133.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.133.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.134.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.134.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.134.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.135.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.135.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.135.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.136.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.136.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.136.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.137.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.137.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.137.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.138.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.138.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.138.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.139.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.139.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.139.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.140.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.140.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.140.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.141.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.141.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.141.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.142.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.142.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.142.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.143.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.143.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.143.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.144.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.144.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.144.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.145.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.145.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.145.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.146.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.146.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.146.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.147.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.147.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.147.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.148.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.148.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.148.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.149.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.149.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.149.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.150.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.150.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.150.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.151.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.151.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.151.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.152.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.152.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.152.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.153.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.153.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.153.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.154.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.154.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.154.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.155.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.155.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.155.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.156.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.156.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.156.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.157.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.157.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.157.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.158.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.158.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.158.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.159.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.159.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.159.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00024-of-00093.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00093.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.128.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.128.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.128.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.129.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.129.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.129.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.130.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.130.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.130.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.131.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.131.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.131.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.132.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.132.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.132.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.133.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.133.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.133.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.134.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.134.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.134.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.135.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.135.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.135.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.136.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.136.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.136.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.137.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.137.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.137.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.138.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.138.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.138.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.139.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.139.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.139.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.140.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.140.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.140.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.141.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.141.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.141.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.142.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.142.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.142.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.143.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.143.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.143.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.144.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.144.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.144.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.145.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.145.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.145.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.146.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.146.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.146.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.147.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.147.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.147.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.148.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.148.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.148.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.149.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.149.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.149.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.150.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.150.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.150.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.151.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.151.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.151.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.152.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.152.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.152.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.153.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.153.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.153.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.154.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.154.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.154.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.155.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.155.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.155.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.156.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.156.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.156.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.157.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.157.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.157.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.158.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.158.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.158.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.159.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.159.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.159.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00025-of-00093.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00093.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.128.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.128.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.128.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.129.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.129.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.129.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.130.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.130.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.130.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.131.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.131.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.131.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.132.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.132.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.132.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.133.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.133.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.133.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.134.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.134.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.134.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.135.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.135.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.135.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.136.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.136.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.136.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.137.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.137.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.137.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.138.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.138.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.138.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.139.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.139.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.139.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.140.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.140.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.140.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.141.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.141.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.141.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.142.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.142.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.142.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.143.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.143.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.143.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.144.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.144.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.144.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.145.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.145.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.145.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.146.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.146.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.146.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.147.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.147.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.147.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.148.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.148.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.148.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.149.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.149.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.149.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.150.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.150.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.150.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.151.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.151.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.151.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.152.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.152.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.152.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.153.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.153.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.153.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.154.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.154.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.154.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.155.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.155.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.155.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.156.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.156.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.156.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.157.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.157.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.157.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.158.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.158.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.158.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.159.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.159.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.159.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00026-of-00093.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00093.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.128.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.128.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.128.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.129.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.129.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.129.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.130.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.130.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.130.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.131.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.131.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.131.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.132.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.132.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.132.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.133.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.133.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.133.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.134.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.134.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.134.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.135.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.135.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.135.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.136.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.136.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.136.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.137.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.137.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.137.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.138.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.138.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.138.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.139.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.139.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.139.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.140.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.140.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.140.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.141.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.141.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.141.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.142.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.142.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.142.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.143.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.143.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.143.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.144.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.144.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.144.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.145.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.145.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.145.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.146.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.146.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.146.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.147.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.147.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.147.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.148.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.148.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.148.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.149.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.149.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.149.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.150.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.150.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.150.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.151.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.151.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.151.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.152.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.152.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.152.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.153.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.153.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.153.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.154.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.154.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.154.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.155.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.155.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.155.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.156.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.156.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.156.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.157.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.157.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.157.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.158.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.158.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.158.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.159.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.159.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.159.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00027-of-00093.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00093.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.128.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.128.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.128.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.129.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.129.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.129.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.130.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.130.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.130.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.131.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.131.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.131.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.132.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.132.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.132.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.133.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.133.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.133.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.134.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.134.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.134.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.135.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.135.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.135.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.136.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.136.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.136.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.137.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.137.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.137.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.138.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.138.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.138.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.139.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.139.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.139.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.140.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.140.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.140.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.141.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.141.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.141.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.142.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.142.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.142.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.143.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.143.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.143.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.144.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.144.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.144.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.145.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.145.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.145.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.146.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.146.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.146.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.147.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.147.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.147.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.148.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.148.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.148.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.149.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.149.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.149.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.150.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.150.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.150.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.151.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.151.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.151.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.152.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.152.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.152.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.153.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.153.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.153.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.154.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.154.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.154.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.155.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.155.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.155.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.156.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.156.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.156.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.157.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.157.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.157.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.158.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.158.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.158.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.159.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.159.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.159.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00028-of-00093.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00093.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.128.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.128.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.128.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.129.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.129.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.129.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.130.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.130.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.130.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.131.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.131.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.131.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.132.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.132.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.132.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.133.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.133.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.133.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.134.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.134.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.134.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.135.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.135.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.135.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.136.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.136.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.136.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.137.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.137.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.137.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.138.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.138.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.138.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.139.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.139.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.139.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.140.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.140.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.140.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.141.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.141.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.141.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.142.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.142.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.142.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.143.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.143.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.143.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.144.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.144.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.144.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.145.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.145.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.145.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.146.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.146.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.146.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.147.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.147.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.147.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.148.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.148.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.148.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.149.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.149.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.149.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.150.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.150.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.150.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.151.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.151.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.151.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.152.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.152.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.152.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.153.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.153.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.153.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.154.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.154.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.154.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.155.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.155.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.155.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.156.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.156.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.156.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.157.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.157.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.157.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.158.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.158.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.158.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.159.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.159.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.159.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00029-of-00093.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00093.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.128.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.128.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.128.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.129.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.129.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.129.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.130.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.130.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.130.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.131.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.131.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.131.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.132.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.132.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.132.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.133.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.133.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.133.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.134.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.134.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.134.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.135.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.135.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.135.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.136.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.136.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.136.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.137.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.137.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.137.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.138.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.138.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.138.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.139.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.139.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.139.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.140.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.140.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.140.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.141.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.141.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.141.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.142.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.142.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.142.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.143.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.143.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.143.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.144.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.144.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.144.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.145.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.145.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.145.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.146.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.146.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.146.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.147.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.147.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.147.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.148.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.148.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.148.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.149.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.149.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.149.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.150.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.150.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.150.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.151.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.151.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.151.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.152.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.152.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.152.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.153.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.153.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.153.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.154.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.154.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.154.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.155.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.155.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.155.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.156.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.156.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.156.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.157.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.157.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.157.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.158.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.158.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.158.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.159.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.159.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.159.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00030-of-00093.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00093.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.128.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.128.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.128.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.129.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.129.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.129.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.130.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.130.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.130.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.131.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.131.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.131.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.132.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.132.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.132.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.133.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.133.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.133.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.134.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.134.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.134.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.135.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.135.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.135.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.136.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.136.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.136.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.137.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.137.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.137.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.138.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.138.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.138.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.139.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.139.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.139.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.140.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.140.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.140.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.141.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.141.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.141.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.142.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.142.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.142.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.143.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.143.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.143.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.144.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.144.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.144.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.145.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.145.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.145.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.146.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.146.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.146.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.147.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.147.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.147.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.148.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.148.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.148.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.149.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.149.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.149.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.150.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.150.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.150.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.151.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.151.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.151.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.152.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.152.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.152.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.153.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.153.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.153.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.154.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.154.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.154.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.155.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.155.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.155.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.156.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.156.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.156.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.157.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.157.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.157.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.158.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.158.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.158.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.159.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.159.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.159.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00031-of-00093.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00093.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.128.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.128.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.128.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.129.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.129.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.129.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.130.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.130.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.130.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.131.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.131.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.131.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.132.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.132.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.132.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.133.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.133.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.133.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.134.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.134.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.134.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.135.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.135.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.135.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.136.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.136.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.136.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.137.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.137.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.137.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.138.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.138.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.138.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.139.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.139.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.139.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.140.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.140.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.140.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.141.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.141.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.141.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.142.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.142.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.142.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.143.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.143.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.143.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.144.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.144.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.144.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.145.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.145.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.145.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.146.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.146.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.146.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.147.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.147.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.147.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.148.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.148.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.148.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.149.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.149.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.149.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.150.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.150.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.150.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.151.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.151.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.151.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.152.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.152.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.152.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.153.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.153.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.153.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.154.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.154.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.154.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.155.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.155.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.155.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.156.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.156.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.156.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.157.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.157.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.157.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.158.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.158.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.158.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.159.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.159.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.159.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00032-of-00093.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00093.safetensors", + "model.layers.32.input_layernorm.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.128.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.128.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.128.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.129.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.129.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.129.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.130.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.130.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.130.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.131.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.131.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.131.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.132.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.132.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.132.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.133.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.133.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.133.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.134.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.134.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.134.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.135.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.135.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.135.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.136.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.136.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.136.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.137.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.137.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.137.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.138.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.138.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.138.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.139.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.139.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.139.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.140.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.140.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.140.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.141.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.141.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.141.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.142.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.142.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.142.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.143.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.143.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.143.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.144.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.144.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.144.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.145.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.145.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.145.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.146.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.146.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.146.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.147.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.147.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.147.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.148.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.148.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.148.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.149.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.149.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.149.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.150.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.150.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.150.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.151.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.151.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.151.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.152.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.152.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.152.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.153.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.153.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.153.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.154.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.154.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.154.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.155.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.155.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.155.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.156.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.156.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.156.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.157.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.157.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.157.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.158.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.158.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.158.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.159.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.159.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.159.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00033-of-00093.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00033-of-00093.safetensors", + "model.layers.33.input_layernorm.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.128.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.128.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.128.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.129.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.129.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.129.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.130.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.130.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.130.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.131.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.131.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.131.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.132.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.132.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.132.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.133.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.133.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.133.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.134.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.134.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.134.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.135.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.135.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.135.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.136.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.136.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.136.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.137.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.137.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.137.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.138.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.138.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.138.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.139.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.139.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.139.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.140.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.140.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.140.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.141.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.141.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.141.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.142.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.142.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.142.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.143.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.143.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.143.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.144.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.144.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.144.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.145.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.145.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.145.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.146.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.146.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.146.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.147.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.147.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.147.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.148.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.148.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.148.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.149.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.149.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.149.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.150.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.150.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.150.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.151.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.151.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.151.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.152.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.152.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.152.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.153.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.153.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.153.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.154.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.154.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.154.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.155.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.155.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.155.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.156.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.156.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.156.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.157.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.157.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.157.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.158.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.158.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.158.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.159.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.159.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.159.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00034-of-00093.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00034-of-00093.safetensors", + "model.layers.34.input_layernorm.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.128.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.128.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.128.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.129.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.129.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.129.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.130.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.130.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.130.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.131.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.131.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.131.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.132.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.132.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.132.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.133.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.133.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.133.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.134.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.134.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.134.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.135.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.135.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.135.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.136.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.136.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.136.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.137.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.137.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.137.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.138.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.138.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.138.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.139.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.139.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.139.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.140.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.140.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.140.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.141.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.141.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.141.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.142.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.142.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.142.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.143.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.143.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.143.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.144.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.144.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.144.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.145.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.145.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.145.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.146.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.146.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.146.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.147.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.147.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.147.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.148.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.148.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.148.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.149.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.149.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.149.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.150.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.150.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.150.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.151.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.151.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.151.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.152.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.152.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.152.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.153.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.153.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.153.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.154.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.154.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.154.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.155.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.155.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.155.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.156.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.156.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.156.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.157.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.157.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.157.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.158.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.158.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.158.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.159.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.159.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.159.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00035-of-00093.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00035-of-00093.safetensors", + "model.layers.35.input_layernorm.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.128.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.128.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.128.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.129.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.129.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.129.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.130.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.130.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.130.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.131.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.131.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.131.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.132.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.132.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.132.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.133.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.133.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.133.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.134.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.134.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.134.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.135.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.135.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.135.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.136.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.136.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.136.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.137.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.137.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.137.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.138.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.138.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.138.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.139.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.139.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.139.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.140.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.140.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.140.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.141.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.141.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.141.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.142.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.142.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.142.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.143.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.143.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.143.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.144.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.144.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.144.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.145.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.145.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.145.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.146.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.146.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.146.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.147.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.147.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.147.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.148.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.148.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.148.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.149.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.149.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.149.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.150.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.150.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.150.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.151.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.151.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.151.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.152.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.152.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.152.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.153.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.153.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.153.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.154.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.154.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.154.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.155.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.155.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.155.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.156.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.156.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.156.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.157.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.157.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.157.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.158.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.158.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.158.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.159.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.159.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.159.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00036-of-00093.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00036-of-00093.safetensors", + "model.layers.36.input_layernorm.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.128.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.128.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.128.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.129.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.129.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.129.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.130.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.130.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.130.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.131.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.131.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.131.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.132.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.132.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.132.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.133.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.133.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.133.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.134.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.134.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.134.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.135.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.135.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.135.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.136.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.136.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.136.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.137.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.137.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.137.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.138.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.138.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.138.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.139.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.139.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.139.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.140.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.140.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.140.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.141.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.141.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.141.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.142.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.142.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.142.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.143.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.143.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.143.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.144.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.144.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.144.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.145.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.145.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.145.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.146.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.146.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.146.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.147.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.147.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.147.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.148.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.148.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.148.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.149.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.149.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.149.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.150.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.150.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.150.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.151.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.151.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.151.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.152.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.152.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.152.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.153.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.153.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.153.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.154.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.154.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.154.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.155.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.155.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.155.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.156.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.156.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.156.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.157.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.157.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.157.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.158.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.158.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.158.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.159.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.159.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.159.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00037-of-00093.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00037-of-00093.safetensors", + "model.layers.37.input_layernorm.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.128.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.128.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.128.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.129.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.129.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.129.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.130.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.130.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.130.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.131.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.131.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.131.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.132.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.132.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.132.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.133.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.133.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.133.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.134.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.134.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.134.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.135.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.135.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.135.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.136.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.136.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.136.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.137.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.137.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.137.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.138.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.138.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.138.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.139.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.139.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.139.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.140.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.140.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.140.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.141.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.141.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.141.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.142.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.142.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.142.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.143.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.143.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.143.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.144.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.144.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.144.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.145.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.145.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.145.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.146.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.146.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.146.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.147.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.147.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.147.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.148.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.148.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.148.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.149.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.149.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.149.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.150.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.150.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.150.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.151.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.151.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.151.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.152.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.152.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.152.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.153.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.153.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.153.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.154.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.154.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.154.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.155.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.155.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.155.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.156.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.156.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.156.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.157.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.157.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.157.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.158.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.158.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.158.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.159.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.159.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.159.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00038-of-00093.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00038-of-00093.safetensors", + "model.layers.38.input_layernorm.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.128.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.128.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.128.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.129.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.129.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.129.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.130.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.130.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.130.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.131.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.131.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.131.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.132.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.132.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.132.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.133.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.133.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.133.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.134.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.134.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.134.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.135.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.135.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.135.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.136.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.136.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.136.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.137.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.137.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.137.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.138.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.138.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.138.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.139.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.139.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.139.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.140.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.140.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.140.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.141.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.141.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.141.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.142.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.142.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.142.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.143.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.143.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.143.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.144.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.144.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.144.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.145.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.145.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.145.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.146.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.146.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.146.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.147.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.147.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.147.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.148.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.148.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.148.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.149.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.149.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.149.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.150.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.150.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.150.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.151.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.151.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.151.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.152.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.152.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.152.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.153.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.153.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.153.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.154.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.154.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.154.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.155.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.155.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.155.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.156.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.156.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.156.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.157.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.157.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.157.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.158.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.158.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.158.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.159.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.159.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.159.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00039-of-00093.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00039-of-00093.safetensors", + "model.layers.39.input_layernorm.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.128.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.128.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.128.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.129.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.129.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.129.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.130.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.130.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.130.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.131.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.131.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.131.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.132.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.132.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.132.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.133.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.133.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.133.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.134.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.134.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.134.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.135.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.135.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.135.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.136.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.136.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.136.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.137.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.137.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.137.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.138.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.138.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.138.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.139.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.139.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.139.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.140.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.140.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.140.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.141.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.141.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.141.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.142.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.142.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.142.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.143.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.143.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.143.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.144.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.144.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.144.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.145.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.145.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.145.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.146.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.146.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.146.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.147.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.147.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.147.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.148.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.148.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.148.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.149.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.149.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.149.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.150.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.150.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.150.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.151.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.151.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.151.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.152.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.152.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.152.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.153.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.153.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.153.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.154.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.154.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.154.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.155.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.155.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.155.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.156.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.156.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.156.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.157.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.157.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.157.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.158.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.158.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.158.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.159.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.159.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.159.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00040-of-00093.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00040-of-00093.safetensors", + "model.layers.40.input_layernorm.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.128.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.128.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.128.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.129.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.129.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.129.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.130.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.130.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.130.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.131.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.131.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.131.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.132.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.132.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.132.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.133.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.133.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.133.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.134.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.134.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.134.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.135.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.135.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.135.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.136.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.136.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.136.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.137.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.137.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.137.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.138.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.138.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.138.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.139.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.139.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.139.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.140.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.140.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.140.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.141.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.141.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.141.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.142.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.142.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.142.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.143.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.143.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.143.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.144.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.144.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.144.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.145.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.145.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.145.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.146.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.146.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.146.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.147.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.147.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.147.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.148.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.148.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.148.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.149.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.149.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.149.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.150.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.150.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.150.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.151.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.151.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.151.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.152.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.152.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.152.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.153.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.153.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.153.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.154.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.154.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.154.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.155.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.155.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.155.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.156.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.156.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.156.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.157.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.157.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.157.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.158.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.158.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.158.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.159.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.159.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.159.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00041-of-00093.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00041-of-00093.safetensors", + "model.layers.41.input_layernorm.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.128.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.128.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.128.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.129.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.129.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.129.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.130.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.130.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.130.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.131.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.131.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.131.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.132.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.132.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.132.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.133.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.133.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.133.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.134.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.134.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.134.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.135.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.135.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.135.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.136.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.136.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.136.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.137.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.137.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.137.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.138.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.138.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.138.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.139.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.139.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.139.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.140.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.140.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.140.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.141.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.141.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.141.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.142.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.142.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.142.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.143.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.143.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.143.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.144.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.144.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.144.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.145.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.145.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.145.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.146.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.146.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.146.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.147.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.147.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.147.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.148.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.148.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.148.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.149.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.149.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.149.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.150.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.150.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.150.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.151.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.151.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.151.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.152.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.152.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.152.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.153.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.153.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.153.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.154.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.154.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.154.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.155.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.155.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.155.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.156.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.156.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.156.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.157.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.157.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.157.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.158.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.158.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.158.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.159.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.159.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.159.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00042-of-00093.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00042-of-00093.safetensors", + "model.layers.42.input_layernorm.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.128.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.128.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.128.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.129.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.129.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.129.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.130.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.130.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.130.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.131.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.131.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.131.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.132.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.132.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.132.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.133.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.133.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.133.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.134.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.134.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.134.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.135.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.135.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.135.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.136.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.136.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.136.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.137.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.137.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.137.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.138.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.138.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.138.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.139.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.139.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.139.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.140.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.140.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.140.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.141.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.141.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.141.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.142.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.142.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.142.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.143.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.143.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.143.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.144.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.144.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.144.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.145.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.145.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.145.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.146.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.146.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.146.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.147.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.147.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.147.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.148.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.148.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.148.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.149.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.149.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.149.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.150.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.150.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.150.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.151.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.151.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.151.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.152.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.152.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.152.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.153.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.153.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.153.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.154.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.154.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.154.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.155.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.155.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.155.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.156.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.156.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.156.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.157.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.157.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.157.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.158.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.158.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.158.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.159.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.159.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.159.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00043-of-00093.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00043-of-00093.safetensors", + "model.layers.43.input_layernorm.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.128.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.128.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.128.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.129.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.129.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.129.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.130.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.130.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.130.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.131.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.131.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.131.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.132.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.132.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.132.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.133.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.133.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.133.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.134.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.134.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.134.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.135.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.135.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.135.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.136.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.136.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.136.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.137.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.137.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.137.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.138.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.138.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.138.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.139.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.139.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.139.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.140.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.140.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.140.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.141.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.141.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.141.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.142.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.142.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.142.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.143.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.143.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.143.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.144.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.144.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.144.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.145.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.145.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.145.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.146.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.146.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.146.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.147.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.147.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.147.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.148.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.148.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.148.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.149.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.149.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.149.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.150.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.150.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.150.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.151.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.151.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.151.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.152.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.152.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.152.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.153.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.153.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.153.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.154.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.154.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.154.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.155.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.155.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.155.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.156.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.156.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.156.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.157.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.157.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.157.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.158.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.158.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.158.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.159.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.159.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.159.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00044-of-00093.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00044-of-00093.safetensors", + "model.layers.44.input_layernorm.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.128.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.128.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.128.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.129.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.129.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.129.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.130.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.130.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.130.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.131.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.131.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.131.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.132.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.132.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.132.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.133.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.133.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.133.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.134.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.134.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.134.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.135.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.135.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.135.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.136.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.136.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.136.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.137.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.137.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.137.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.138.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.138.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.138.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.139.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.139.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.139.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.140.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.140.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.140.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.141.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.141.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.141.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.142.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.142.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.142.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.143.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.143.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.143.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.144.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.144.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.144.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.145.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.145.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.145.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.146.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.146.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.146.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.147.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.147.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.147.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.148.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.148.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.148.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.149.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.149.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.149.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.150.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.150.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.150.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.151.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.151.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.151.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.152.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.152.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.152.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.153.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.153.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.153.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.154.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.154.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.154.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.155.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.155.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.155.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.156.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.156.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.156.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.157.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.157.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.157.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.158.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.158.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.158.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.159.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.159.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.159.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00045-of-00093.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00045-of-00093.safetensors", + "model.layers.45.input_layernorm.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.128.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.128.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.128.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.129.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.129.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.129.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.130.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.130.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.130.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.131.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.131.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.131.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.132.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.132.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.132.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.133.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.133.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.133.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.134.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.134.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.134.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.135.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.135.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.135.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.136.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.136.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.136.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.137.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.137.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.137.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.138.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.138.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.138.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.139.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.139.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.139.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.140.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.140.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.140.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.141.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.141.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.141.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.142.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.142.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.142.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.143.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.143.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.143.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.144.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.144.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.144.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.145.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.145.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.145.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.146.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.146.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.146.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.147.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.147.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.147.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.148.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.148.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.148.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.149.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.149.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.149.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.150.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.150.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.150.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.151.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.151.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.151.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.152.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.152.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.152.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.153.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.153.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.153.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.154.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.154.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.154.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.155.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.155.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.155.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.156.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.156.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.156.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.157.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.157.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.157.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.158.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.158.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.158.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.159.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.159.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.159.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00046-of-00093.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00046-of-00093.safetensors", + "model.layers.46.input_layernorm.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.100.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.100.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.100.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.101.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.101.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.101.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.102.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.102.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.102.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.103.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.103.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.103.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.104.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.104.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.104.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.105.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.105.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.105.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.106.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.106.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.106.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.107.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.107.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.107.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.108.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.108.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.108.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.109.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.109.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.109.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.110.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.110.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.110.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.111.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.111.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.111.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.112.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.112.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.112.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.113.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.113.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.113.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.114.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.114.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.114.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.115.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.115.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.115.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.116.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.116.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.116.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.117.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.117.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.117.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.118.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.118.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.118.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.119.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.119.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.119.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.120.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.120.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.120.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.121.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.121.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.121.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.122.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.122.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.122.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.123.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.123.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.123.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.124.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.124.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.124.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.125.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.125.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.125.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.126.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.126.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.126.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.127.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.127.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.127.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.128.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.128.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.128.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.129.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.129.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.129.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.130.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.130.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.130.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.131.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.131.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.131.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.132.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.132.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.132.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.133.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.133.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.133.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.134.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.134.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.134.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.135.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.135.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.135.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.136.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.136.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.136.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.137.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.137.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.137.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.138.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.138.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.138.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.139.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.139.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.139.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.140.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.140.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.140.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.141.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.141.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.141.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.142.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.142.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.142.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.143.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.143.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.143.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.144.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.144.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.144.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.145.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.145.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.145.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.146.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.146.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.146.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.147.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.147.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.147.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.148.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.148.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.148.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.149.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.149.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.149.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.150.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.150.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.150.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.151.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.151.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.151.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.152.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.152.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.152.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.153.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.153.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.153.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.154.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.154.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.154.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.155.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.155.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.155.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.156.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.156.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.156.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.157.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.157.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.157.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.158.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.158.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.158.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.159.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.159.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.159.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.64.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.64.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.64.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.65.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.65.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.65.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.66.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.66.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.66.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.67.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.67.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.67.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.68.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.68.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.68.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.69.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.69.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.69.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.70.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.70.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.70.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.71.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.71.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.71.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.72.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.72.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.72.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.73.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.73.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.73.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.74.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.74.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.74.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.75.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.75.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.75.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.76.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.76.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.76.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.77.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.77.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.77.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.78.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.78.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.78.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.79.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.79.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.79.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.80.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.80.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.80.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.81.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.81.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.81.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.82.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.82.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.82.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.83.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.83.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.83.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.84.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.84.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.84.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.85.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.85.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.85.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.86.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.86.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.86.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.87.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.87.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.87.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.88.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.88.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.88.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.89.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.89.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.89.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.90.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.90.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.90.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.91.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.91.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.91.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.92.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.92.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.92.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.93.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.93.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.93.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.94.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.94.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.94.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.95.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.95.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.95.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.96.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.96.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.96.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.97.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.97.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.97.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.98.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.98.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.98.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.99.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.99.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.experts.99.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.gate.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00047-of-00093.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00047-of-00093.safetensors", + "model.layers.47.input_layernorm.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.100.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.100.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.100.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.101.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.101.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.101.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.102.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.102.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.102.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.103.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.103.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.103.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.104.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.104.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.104.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.105.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.105.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.105.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.106.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.106.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.106.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.107.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.107.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.107.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.108.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.108.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.108.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.109.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.109.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.109.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.110.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.110.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.110.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.111.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.111.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.111.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.112.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.112.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.112.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.113.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.113.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.113.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.114.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.114.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.114.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.115.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.115.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.115.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.116.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.116.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.116.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.117.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.117.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.117.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.118.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.118.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.118.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.119.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.119.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.119.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.120.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.120.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.120.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.121.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.121.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.121.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.122.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.122.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.122.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.123.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.123.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.123.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.124.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.124.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.124.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.125.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.125.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.125.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.126.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.126.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.126.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.127.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.127.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.127.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.128.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.128.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.128.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.129.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.129.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.129.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.130.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.130.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.130.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.131.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.131.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.131.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.132.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.132.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.132.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.133.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.133.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.133.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.134.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.134.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.134.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.135.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.135.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.135.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.136.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.136.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.136.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.137.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.137.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.137.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.138.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.138.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.138.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.139.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.139.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.139.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.140.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.140.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.140.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.141.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.141.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.141.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.142.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.142.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.142.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.143.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.143.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.143.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.144.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.144.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.144.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.145.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.145.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.145.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.146.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.146.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.146.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.147.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.147.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.147.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.148.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.148.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.148.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.149.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.149.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.149.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.150.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.150.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.150.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.151.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.151.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.151.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.152.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.152.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.152.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.153.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.153.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.153.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.154.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.154.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.154.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.155.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.155.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.155.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.156.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.156.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.156.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.157.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.157.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.157.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.158.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.158.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.158.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.159.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.159.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.159.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.64.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.64.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.64.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.65.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.65.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.65.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.66.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.66.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.66.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.67.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.67.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.67.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.68.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.68.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.68.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.69.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.69.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.69.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.70.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.70.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.70.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.71.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.71.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.71.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.72.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.72.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.72.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.73.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.73.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.73.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.74.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.74.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.74.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.75.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.75.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.75.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.76.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.76.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.76.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.77.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.77.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.77.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.78.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.78.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.78.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.79.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.79.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.79.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.80.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.80.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.80.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.81.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.81.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.81.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.82.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.82.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.82.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.83.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.83.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.83.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.84.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.84.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.84.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.85.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.85.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.85.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.86.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.86.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.86.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.87.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.87.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.87.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.88.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.88.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.88.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.89.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.89.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.89.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.90.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.90.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.90.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.91.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.91.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.91.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.92.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.92.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.92.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.93.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.93.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.93.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.94.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.94.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.94.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.95.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.95.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.95.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.96.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.96.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.96.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.97.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.97.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.97.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.98.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.98.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.98.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.99.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.99.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.experts.99.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.gate.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00048-of-00093.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00048-of-00093.safetensors", + "model.layers.48.input_layernorm.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.0.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.0.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.0.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.1.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.1.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.1.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.10.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.10.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.10.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.100.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.100.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.100.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.101.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.101.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.101.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.102.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.102.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.102.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.103.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.103.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.103.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.104.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.104.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.104.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.105.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.105.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.105.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.106.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.106.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.106.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.107.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.107.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.107.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.108.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.108.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.108.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.109.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.109.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.109.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.11.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.11.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.11.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.110.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.110.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.110.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.111.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.111.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.111.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.112.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.112.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.112.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.113.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.113.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.113.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.114.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.114.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.114.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.115.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.115.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.115.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.116.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.116.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.116.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.117.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.117.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.117.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.118.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.118.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.118.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.119.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.119.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.119.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.12.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.12.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.12.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.120.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.120.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.120.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.121.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.121.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.121.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.122.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.122.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.122.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.123.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.123.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.123.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.124.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.124.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.124.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.125.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.125.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.125.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.126.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.126.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.126.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.127.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.127.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.127.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.128.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.128.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.128.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.129.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.129.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.129.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.13.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.13.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.13.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.130.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.130.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.130.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.131.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.131.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.131.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.132.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.132.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.132.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.133.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.133.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.133.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.134.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.134.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.134.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.135.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.135.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.135.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.136.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.136.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.136.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.137.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.137.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.137.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.138.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.138.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.138.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.139.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.139.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.139.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.14.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.14.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.14.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.140.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.140.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.140.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.141.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.141.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.141.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.142.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.142.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.142.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.143.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.143.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.143.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.144.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.144.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.144.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.145.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.145.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.145.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.146.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.146.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.146.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.147.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.147.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.147.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.148.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.148.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.148.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.149.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.149.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.149.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.15.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.15.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.15.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.150.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.150.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.150.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.151.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.151.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.151.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.152.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.152.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.152.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.153.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.153.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.153.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.154.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.154.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.154.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.155.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.155.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.155.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.156.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.156.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.156.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.157.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.157.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.157.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.158.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.158.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.158.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.159.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.159.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.159.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.16.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.16.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.16.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.17.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.17.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.17.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.18.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.18.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.18.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.19.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.19.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.19.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.2.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.2.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.2.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.20.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.20.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.20.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.21.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.21.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.21.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.22.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.22.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.22.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.23.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.23.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.23.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.24.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.24.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.24.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.25.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.25.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.25.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.26.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.26.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.26.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.27.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.27.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.27.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.28.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.28.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.28.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.29.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.29.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.29.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.3.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.3.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.3.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.30.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.30.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.30.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.31.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.31.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.31.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.32.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.32.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.32.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.33.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.33.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.33.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.34.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.34.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.34.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.35.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.35.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.35.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.36.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.36.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.36.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.37.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.37.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.37.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.38.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.38.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.38.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.39.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.39.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.39.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.4.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.4.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.4.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.40.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.40.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.40.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.41.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.41.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.41.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.42.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.42.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.42.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.43.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.43.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.43.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.44.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.44.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.44.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.45.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.45.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.45.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.46.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.46.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.46.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.47.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.47.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.47.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.48.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.48.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.48.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.49.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.49.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.49.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.5.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.5.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.5.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.50.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.50.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.50.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.51.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.51.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.51.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.52.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.52.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.52.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.53.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.53.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.53.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.54.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.54.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.54.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.55.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.55.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.55.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.56.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.56.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.56.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.57.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.57.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.57.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.58.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.58.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.58.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.59.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.59.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.59.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.6.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.6.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.6.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.60.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.60.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.60.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.61.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.61.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.61.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.62.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.62.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.62.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.63.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.63.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.63.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.64.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.64.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.64.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.65.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.65.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.65.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.66.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.66.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.66.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.67.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.67.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.67.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.68.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.68.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.68.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.69.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.69.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.69.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.7.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.7.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.7.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.70.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.70.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.70.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.71.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.71.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.71.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.72.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.72.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.72.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.73.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.73.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.73.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.74.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.74.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.74.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.75.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.75.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.75.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.76.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.76.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.76.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.77.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.77.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.77.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.78.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.78.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.78.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.79.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.79.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.79.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.8.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.8.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.8.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.80.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.80.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.80.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.81.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.81.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.81.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.82.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.82.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.82.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.83.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.83.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.83.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.84.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.84.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.84.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.85.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.85.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.85.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.86.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.86.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.86.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.87.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.87.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.87.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.88.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.88.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.88.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.89.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.89.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.89.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.9.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.9.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.9.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.90.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.90.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.90.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.91.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.91.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.91.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.92.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.92.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.92.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.93.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.93.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.93.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.94.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.94.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.94.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.95.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.95.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.95.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.96.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.96.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.96.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.97.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.97.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.97.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.98.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.98.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.98.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.99.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.99.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.experts.99.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.gate.e_score_correction_bias": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.gate.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00049-of-00093.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00049-of-00093.safetensors", + "model.layers.49.input_layernorm.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.0.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.0.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.0.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.1.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.1.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.1.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.10.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.10.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.10.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.100.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.100.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.100.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.101.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.101.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.101.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.102.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.102.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.102.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.103.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.103.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.103.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.104.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.104.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.104.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.105.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.105.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.105.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.106.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.106.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.106.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.107.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.107.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.107.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.108.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.108.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.108.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.109.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.109.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.109.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.11.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.11.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.11.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.110.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.110.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.110.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.111.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.111.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.111.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.112.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.112.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.112.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.113.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.113.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.113.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.114.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.114.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.114.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.115.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.115.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.115.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.116.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.116.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.116.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.117.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.117.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.117.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.118.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.118.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.118.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.119.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.119.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.119.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.12.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.12.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.12.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.120.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.120.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.120.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.121.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.121.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.121.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.122.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.122.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.122.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.123.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.123.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.123.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.124.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.124.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.124.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.125.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.125.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.125.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.126.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.126.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.126.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.127.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.127.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.127.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.128.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.128.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.128.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.129.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.129.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.129.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.13.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.13.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.13.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.130.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.130.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.130.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.131.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.131.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.131.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.132.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.132.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.132.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.133.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.133.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.133.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.134.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.134.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.134.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.135.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.135.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.135.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.136.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.136.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.136.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.137.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.137.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.137.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.138.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.138.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.138.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.139.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.139.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.139.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.14.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.14.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.14.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.140.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.140.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.140.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.141.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.141.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.141.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.142.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.142.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.142.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.143.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.143.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.143.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.144.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.144.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.144.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.145.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.145.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.145.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.146.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.146.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.146.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.147.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.147.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.147.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.148.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.148.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.148.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.149.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.149.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.149.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.15.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.15.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.15.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.150.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.150.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.150.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.151.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.151.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.151.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.152.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.152.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.152.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.153.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.153.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.153.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.154.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.154.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.154.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.155.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.155.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.155.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.156.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.156.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.156.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.157.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.157.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.157.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.158.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.158.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.158.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.159.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.159.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.159.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.16.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.16.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.16.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.17.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.17.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.17.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.18.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.18.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.18.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.19.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.19.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.19.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.2.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.2.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.2.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.20.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.20.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.20.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.21.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.21.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.21.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.22.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.22.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.22.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.23.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.23.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.23.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.24.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.24.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.24.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.25.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.25.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.25.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.26.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.26.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.26.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.27.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.27.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.27.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.28.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.28.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.28.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.29.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.29.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.29.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.3.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.3.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.3.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.30.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.30.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.30.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.31.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.31.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.31.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.32.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.32.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.32.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.33.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.33.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.33.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.34.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.34.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.34.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.35.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.35.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.35.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.36.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.36.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.36.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.37.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.37.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.37.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.38.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.38.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.38.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.39.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.39.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.39.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.4.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.4.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.4.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.40.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.40.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.40.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.41.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.41.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.41.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.42.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.42.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.42.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.43.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.43.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.43.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.44.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.44.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.44.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.45.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.45.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.45.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.46.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.46.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.46.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.47.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.47.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.47.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.48.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.48.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.48.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.49.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.49.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.49.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.5.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.5.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.5.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.50.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.50.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.50.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.51.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.51.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.51.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.52.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.52.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.52.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.53.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.53.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.53.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.54.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.54.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.54.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.55.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.55.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.55.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.56.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.56.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.56.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.57.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.57.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.57.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.58.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.58.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.58.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.59.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.59.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.59.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.6.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.6.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.6.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.60.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.60.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.60.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.61.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.61.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.61.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.62.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.62.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.62.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.63.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.63.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.63.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.64.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.64.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.64.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.65.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.65.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.65.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.66.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.66.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.66.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.67.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.67.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.67.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.68.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.68.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.68.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.69.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.69.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.69.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.7.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.7.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.7.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.70.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.70.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.70.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.71.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.71.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.71.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.72.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.72.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.72.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.73.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.73.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.73.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.74.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.74.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.74.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.75.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.75.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.75.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.76.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.76.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.76.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.77.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.77.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.77.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.78.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.78.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.78.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.79.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.79.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.79.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.8.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.8.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.8.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.80.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.80.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.80.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.81.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.81.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.81.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.82.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.82.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.82.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.83.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.83.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.83.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.84.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.84.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.84.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.85.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.85.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.85.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.86.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.86.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.86.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.87.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.87.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.87.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.88.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.88.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.88.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.89.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.89.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.89.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.9.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.9.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.9.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.90.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.90.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.90.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.91.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.91.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.91.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.92.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.92.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.92.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.93.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.93.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.93.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.94.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.94.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.94.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.95.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.95.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.95.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.96.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.96.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.96.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.97.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.97.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.97.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.98.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.98.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.98.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.99.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.99.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.experts.99.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.gate.e_score_correction_bias": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.gate.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00050-of-00093.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00050-of-00093.safetensors", + "model.layers.50.input_layernorm.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.0.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.0.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.0.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.1.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.1.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.1.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.10.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.10.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.10.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.100.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.100.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.100.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.101.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.101.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.101.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.102.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.102.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.102.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.103.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.103.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.103.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.104.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.104.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.104.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.105.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.105.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.105.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.106.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.106.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.106.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.107.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.107.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.107.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.108.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.108.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.108.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.109.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.109.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.109.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.11.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.11.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.11.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.110.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.110.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.110.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.111.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.111.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.111.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.112.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.112.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.112.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.113.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.113.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.113.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.114.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.114.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.114.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.115.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.115.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.115.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.116.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.116.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.116.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.117.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.117.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.117.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.118.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.118.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.118.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.119.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.119.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.119.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.12.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.12.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.12.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.120.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.120.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.120.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.121.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.121.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.121.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.122.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.122.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.122.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.123.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.123.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.123.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.124.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.124.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.124.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.125.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.125.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.125.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.126.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.126.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.126.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.127.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.127.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.127.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.128.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.128.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.128.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.129.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.129.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.129.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.13.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.13.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.13.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.130.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.130.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.130.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.131.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.131.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.131.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.132.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.132.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.132.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.133.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.133.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.133.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.134.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.134.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.134.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.135.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.135.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.135.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.136.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.136.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.136.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.137.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.137.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.137.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.138.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.138.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.138.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.139.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.139.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.139.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.14.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.14.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.14.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.140.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.140.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.140.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.141.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.141.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.141.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.142.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.142.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.142.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.143.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.143.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.143.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.144.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.144.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.144.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.145.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.145.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.145.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.146.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.146.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.146.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.147.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.147.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.147.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.148.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.148.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.148.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.149.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.149.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.149.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.15.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.15.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.15.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.150.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.150.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.150.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.151.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.151.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.151.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.152.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.152.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.152.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.153.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.153.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.153.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.154.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.154.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.154.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.155.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.155.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.155.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.156.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.156.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.156.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.157.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.157.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.157.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.158.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.158.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.158.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.159.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.159.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.159.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.16.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.16.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.16.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.17.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.17.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.17.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.18.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.18.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.18.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.19.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.19.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.19.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.2.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.2.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.2.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.20.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.20.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.20.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.21.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.21.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.21.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.22.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.22.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.22.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.23.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.23.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.23.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.24.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.24.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.24.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.25.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.25.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.25.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.26.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.26.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.26.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.27.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.27.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.27.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.28.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.28.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.28.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.29.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.29.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.29.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.3.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.3.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.3.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.30.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.30.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.30.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.31.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.31.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.31.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.32.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.32.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.32.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.33.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.33.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.33.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.34.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.34.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.34.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.35.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.35.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.35.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.36.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.36.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.36.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.37.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.37.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.37.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.38.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.38.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.38.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.39.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.39.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.39.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.4.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.4.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.4.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.40.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.40.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.40.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.41.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.41.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.41.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.42.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.42.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.42.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.43.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.43.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.43.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.44.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.44.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.44.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.45.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.45.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.45.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.46.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.46.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.46.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.47.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.47.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.47.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.48.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.48.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.48.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.49.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.49.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.49.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.5.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.5.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.5.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.50.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.50.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.50.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.51.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.51.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.51.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.52.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.52.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.52.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.53.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.53.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.53.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.54.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.54.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.54.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.55.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.55.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.55.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.56.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.56.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.56.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.57.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.57.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.57.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.58.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.58.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.58.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.59.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.59.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.59.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.6.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.6.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.6.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.60.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.60.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.60.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.61.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.61.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.61.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.62.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.62.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.62.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.63.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.63.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.63.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.64.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.64.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.64.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.65.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.65.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.65.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.66.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.66.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.66.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.67.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.67.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.67.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.68.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.68.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.68.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.69.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.69.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.69.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.7.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.7.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.7.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.70.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.70.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.70.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.71.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.71.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.71.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.72.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.72.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.72.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.73.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.73.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.73.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.74.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.74.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.74.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.75.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.75.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.75.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.76.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.76.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.76.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.77.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.77.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.77.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.78.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.78.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.78.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.79.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.79.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.79.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.8.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.8.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.8.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.80.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.80.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.80.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.81.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.81.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.81.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.82.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.82.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.82.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.83.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.83.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.83.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.84.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.84.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.84.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.85.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.85.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.85.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.86.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.86.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.86.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.87.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.87.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.87.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.88.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.88.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.88.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.89.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.89.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.89.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.9.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.9.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.9.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.90.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.90.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.90.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.91.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.91.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.91.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.92.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.92.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.92.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.93.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.93.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.93.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.94.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.94.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.94.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.95.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.95.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.95.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.96.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.96.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.96.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.97.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.97.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.97.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.98.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.98.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.98.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.99.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.99.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.experts.99.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.gate.e_score_correction_bias": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.gate.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00051-of-00093.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00051-of-00093.safetensors", + "model.layers.51.input_layernorm.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.0.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.0.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.0.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.1.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.1.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.1.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.10.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.10.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.10.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.100.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.100.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.100.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.101.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.101.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.101.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.102.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.102.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.102.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.103.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.103.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.103.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.104.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.104.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.104.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.105.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.105.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.105.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.106.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.106.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.106.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.107.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.107.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.107.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.108.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.108.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.108.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.109.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.109.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.109.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.11.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.11.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.11.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.110.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.110.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.110.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.111.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.111.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.111.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.112.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.112.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.112.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.113.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.113.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.113.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.114.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.114.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.114.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.115.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.115.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.115.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.116.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.116.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.116.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.117.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.117.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.117.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.118.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.118.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.118.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.119.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.119.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.119.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.12.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.12.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.12.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.120.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.120.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.120.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.121.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.121.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.121.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.122.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.122.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.122.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.123.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.123.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.123.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.124.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.124.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.124.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.125.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.125.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.125.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.126.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.126.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.126.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.127.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.127.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.127.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.128.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.128.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.128.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.129.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.129.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.129.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.13.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.13.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.13.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.130.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.130.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.130.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.131.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.131.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.131.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.132.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.132.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.132.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.133.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.133.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.133.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.134.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.134.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.134.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.135.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.135.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.135.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.136.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.136.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.136.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.137.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.137.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.137.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.138.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.138.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.138.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.139.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.139.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.139.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.14.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.14.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.14.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.140.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.140.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.140.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.141.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.141.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.141.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.142.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.142.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.142.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.143.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.143.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.143.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.144.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.144.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.144.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.145.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.145.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.145.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.146.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.146.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.146.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.147.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.147.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.147.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.148.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.148.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.148.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.149.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.149.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.149.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.15.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.15.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.15.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.150.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.150.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.150.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.151.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.151.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.151.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.152.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.152.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.152.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.153.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.153.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.153.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.154.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.154.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.154.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.155.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.155.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.155.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.156.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.156.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.156.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.157.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.157.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.157.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.158.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.158.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.158.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.159.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.159.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.159.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.16.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.16.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.16.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.17.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.17.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.17.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.18.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.18.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.18.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.19.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.19.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.19.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.2.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.2.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.2.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.20.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.20.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.20.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.21.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.21.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.21.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.22.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.22.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.22.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.23.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.23.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.23.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.24.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.24.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.24.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.25.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.25.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.25.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.26.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.26.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.26.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.27.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.27.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.27.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.28.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.28.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.28.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.29.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.29.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.29.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.3.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.3.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.3.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.30.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.30.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.30.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.31.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.31.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.31.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.32.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.32.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.32.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.33.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.33.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.33.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.34.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.34.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.34.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.35.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.35.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.35.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.36.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.36.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.36.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.37.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.37.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.37.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.38.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.38.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.38.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.39.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.39.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.39.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.4.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.4.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.4.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.40.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.40.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.40.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.41.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.41.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.41.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.42.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.42.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.42.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.43.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.43.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.43.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.44.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.44.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.44.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.45.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.45.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.45.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.46.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.46.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.46.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.47.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.47.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.47.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.48.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.48.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.48.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.49.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.49.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.49.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.5.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.5.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.5.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.50.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.50.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.50.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.51.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.51.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.51.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.52.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.52.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.52.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.53.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.53.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.53.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.54.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.54.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.54.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.55.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.55.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.55.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.56.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.56.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.56.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.57.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.57.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.57.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.58.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.58.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.58.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.59.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.59.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.59.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.6.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.6.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.6.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.60.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.60.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.60.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.61.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.61.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.61.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.62.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.62.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.62.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.63.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.63.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.63.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.64.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.64.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.64.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.65.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.65.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.65.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.66.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.66.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.66.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.67.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.67.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.67.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.68.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.68.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.68.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.69.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.69.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.69.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.7.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.7.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.7.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.70.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.70.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.70.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.71.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.71.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.71.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.72.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.72.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.72.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.73.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.73.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.73.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.74.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.74.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.74.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.75.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.75.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.75.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.76.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.76.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.76.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.77.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.77.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.77.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.78.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.78.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.78.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.79.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.79.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.79.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.8.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.8.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.8.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.80.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.80.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.80.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.81.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.81.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.81.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.82.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.82.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.82.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.83.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.83.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.83.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.84.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.84.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.84.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.85.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.85.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.85.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.86.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.86.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.86.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.87.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.87.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.87.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.88.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.88.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.88.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.89.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.89.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.89.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.9.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.9.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.9.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.90.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.90.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.90.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.91.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.91.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.91.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.92.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.92.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.92.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.93.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.93.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.93.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.94.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.94.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.94.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.95.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.95.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.95.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.96.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.96.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.96.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.97.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.97.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.97.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.98.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.98.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.98.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.99.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.99.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.experts.99.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.gate.e_score_correction_bias": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.gate.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00052-of-00093.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00052-of-00093.safetensors", + "model.layers.52.input_layernorm.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.0.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.0.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.0.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.1.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.1.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.1.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.10.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.10.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.10.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.100.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.100.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.100.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.101.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.101.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.101.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.102.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.102.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.102.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.103.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.103.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.103.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.104.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.104.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.104.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.105.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.105.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.105.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.106.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.106.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.106.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.107.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.107.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.107.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.108.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.108.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.108.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.109.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.109.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.109.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.11.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.11.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.11.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.110.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.110.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.110.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.111.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.111.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.111.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.112.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.112.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.112.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.113.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.113.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.113.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.114.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.114.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.114.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.115.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.115.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.115.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.116.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.116.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.116.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.117.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.117.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.117.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.118.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.118.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.118.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.119.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.119.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.119.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.12.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.12.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.12.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.120.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.120.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.120.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.121.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.121.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.121.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.122.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.122.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.122.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.123.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.123.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.123.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.124.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.124.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.124.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.125.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.125.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.125.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.126.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.126.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.126.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.127.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.127.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.127.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.128.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.128.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.128.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.129.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.129.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.129.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.13.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.13.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.13.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.130.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.130.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.130.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.131.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.131.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.131.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.132.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.132.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.132.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.133.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.133.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.133.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.134.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.134.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.134.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.135.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.135.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.135.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.136.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.136.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.136.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.137.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.137.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.137.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.138.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.138.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.138.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.139.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.139.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.139.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.14.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.14.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.14.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.140.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.140.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.140.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.141.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.141.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.141.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.142.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.142.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.142.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.143.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.143.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.143.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.144.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.144.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.144.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.145.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.145.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.145.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.146.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.146.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.146.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.147.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.147.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.147.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.148.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.148.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.148.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.149.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.149.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.149.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.15.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.15.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.15.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.150.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.150.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.150.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.151.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.151.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.151.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.152.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.152.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.152.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.153.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.153.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.153.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.154.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.154.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.154.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.155.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.155.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.155.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.156.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.156.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.156.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.157.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.157.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.157.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.158.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.158.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.158.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.159.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.159.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.159.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.16.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.16.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.16.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.17.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.17.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.17.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.18.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.18.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.18.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.19.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.19.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.19.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.2.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.2.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.2.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.20.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.20.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.20.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.21.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.21.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.21.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.22.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.22.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.22.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.23.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.23.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.23.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.24.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.24.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.24.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.25.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.25.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.25.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.26.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.26.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.26.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.27.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.27.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.27.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.28.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.28.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.28.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.29.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.29.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.29.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.3.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.3.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.3.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.30.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.30.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.30.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.31.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.31.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.31.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.32.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.32.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.32.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.33.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.33.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.33.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.34.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.34.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.34.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.35.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.35.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.35.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.36.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.36.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.36.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.37.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.37.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.37.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.38.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.38.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.38.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.39.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.39.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.39.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.4.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.4.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.4.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.40.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.40.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.40.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.41.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.41.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.41.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.42.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.42.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.42.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.43.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.43.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.43.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.44.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.44.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.44.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.45.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.45.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.45.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.46.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.46.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.46.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.47.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.47.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.47.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.48.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.48.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.48.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.49.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.49.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.49.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.5.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.5.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.5.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.50.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.50.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.50.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.51.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.51.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.51.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.52.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.52.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.52.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.53.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.53.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.53.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.54.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.54.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.54.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.55.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.55.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.55.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.56.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.56.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.56.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.57.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.57.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.57.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.58.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.58.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.58.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.59.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.59.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.59.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.6.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.6.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.6.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.60.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.60.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.60.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.61.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.61.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.61.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.62.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.62.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.62.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.63.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.63.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.63.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.64.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.64.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.64.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.65.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.65.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.65.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.66.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.66.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.66.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.67.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.67.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.67.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.68.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.68.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.68.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.69.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.69.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.69.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.7.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.7.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.7.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.70.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.70.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.70.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.71.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.71.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.71.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.72.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.72.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.72.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.73.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.73.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.73.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.74.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.74.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.74.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.75.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.75.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.75.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.76.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.76.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.76.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.77.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.77.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.77.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.78.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.78.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.78.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.79.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.79.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.79.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.8.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.8.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.8.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.80.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.80.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.80.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.81.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.81.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.81.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.82.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.82.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.82.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.83.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.83.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.83.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.84.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.84.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.84.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.85.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.85.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.85.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.86.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.86.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.86.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.87.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.87.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.87.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.88.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.88.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.88.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.89.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.89.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.89.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.9.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.9.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.9.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.90.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.90.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.90.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.91.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.91.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.91.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.92.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.92.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.92.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.93.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.93.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.93.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.94.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.94.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.94.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.95.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.95.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.95.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.96.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.96.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.96.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.97.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.97.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.97.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.98.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.98.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.98.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.99.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.99.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.experts.99.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.gate.e_score_correction_bias": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.gate.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00053-of-00093.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00053-of-00093.safetensors", + "model.layers.53.input_layernorm.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.0.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.0.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.0.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.1.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.1.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.1.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.10.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.10.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.10.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.100.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.100.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.100.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.101.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.101.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.101.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.102.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.102.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.102.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.103.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.103.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.103.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.104.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.104.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.104.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.105.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.105.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.105.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.106.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.106.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.106.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.107.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.107.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.107.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.108.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.108.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.108.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.109.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.109.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.109.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.11.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.11.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.11.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.110.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.110.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.110.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.111.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.111.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.111.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.112.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.112.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.112.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.113.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.113.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.113.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.114.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.114.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.114.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.115.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.115.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.115.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.116.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.116.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.116.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.117.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.117.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.117.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.118.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.118.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.118.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.119.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.119.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.119.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.12.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.12.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.12.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.120.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.120.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.120.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.121.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.121.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.121.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.122.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.122.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.122.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.123.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.123.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.123.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.124.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.124.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.124.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.125.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.125.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.125.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.126.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.126.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.126.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.127.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.127.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.127.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.128.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.128.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.128.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.129.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.129.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.129.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.13.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.13.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.13.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.130.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.130.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.130.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.131.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.131.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.131.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.132.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.132.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.132.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.133.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.133.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.133.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.134.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.134.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.134.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.135.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.135.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.135.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.136.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.136.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.136.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.137.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.137.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.137.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.138.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.138.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.138.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.139.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.139.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.139.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.14.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.14.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.14.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.140.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.140.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.140.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.141.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.141.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.141.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.142.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.142.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.142.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.143.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.143.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.143.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.144.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.144.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.144.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.145.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.145.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.145.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.146.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.146.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.146.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.147.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.147.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.147.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.148.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.148.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.148.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.149.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.149.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.149.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.15.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.15.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.15.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.150.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.150.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.150.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.151.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.151.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.151.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.152.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.152.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.152.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.153.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.153.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.153.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.154.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.154.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.154.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.155.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.155.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.155.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.156.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.156.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.156.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.157.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.157.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.157.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.158.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.158.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.158.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.159.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.159.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.159.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.16.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.16.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.16.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.17.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.17.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.17.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.18.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.18.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.18.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.19.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.19.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.19.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.2.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.2.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.2.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.20.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.20.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.20.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.21.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.21.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.21.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.22.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.22.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.22.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.23.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.23.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.23.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.24.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.24.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.24.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.25.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.25.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.25.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.26.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.26.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.26.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.27.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.27.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.27.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.28.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.28.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.28.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.29.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.29.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.29.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.3.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.3.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.3.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.30.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.30.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.30.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.31.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.31.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.31.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.32.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.32.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.32.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.33.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.33.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.33.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.34.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.34.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.34.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.35.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.35.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.35.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.36.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.36.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.36.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.37.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.37.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.37.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.38.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.38.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.38.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.39.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.39.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.39.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.4.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.4.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.4.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.40.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.40.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.40.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.41.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.41.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.41.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.42.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.42.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.42.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.43.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.43.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.43.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.44.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.44.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.44.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.45.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.45.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.45.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.46.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.46.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.46.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.47.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.47.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.47.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.48.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.48.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.48.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.49.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.49.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.49.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.5.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.5.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.5.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.50.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.50.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.50.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.51.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.51.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.51.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.52.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.52.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.52.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.53.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.53.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.53.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.54.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.54.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.54.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.55.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.55.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.55.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.56.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.56.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.56.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.57.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.57.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.57.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.58.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.58.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.58.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.59.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.59.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.59.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.6.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.6.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.6.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.60.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.60.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.60.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.61.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.61.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.61.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.62.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.62.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.62.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.63.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.63.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.63.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.64.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.64.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.64.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.65.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.65.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.65.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.66.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.66.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.66.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.67.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.67.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.67.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.68.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.68.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.68.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.69.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.69.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.69.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.7.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.7.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.7.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.70.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.70.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.70.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.71.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.71.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.71.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.72.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.72.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.72.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.73.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.73.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.73.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.74.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.74.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.74.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.75.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.75.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.75.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.76.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.76.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.76.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.77.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.77.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.77.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.78.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.78.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.78.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.79.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.79.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.79.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.8.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.8.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.8.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.80.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.80.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.80.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.81.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.81.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.81.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.82.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.82.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.82.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.83.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.83.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.83.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.84.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.84.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.84.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.85.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.85.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.85.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.86.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.86.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.86.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.87.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.87.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.87.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.88.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.88.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.88.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.89.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.89.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.89.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.9.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.9.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.9.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.90.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.90.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.90.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.91.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.91.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.91.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.92.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.92.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.92.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.93.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.93.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.93.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.94.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.94.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.94.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.95.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.95.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.95.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.96.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.96.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.96.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.97.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.97.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.97.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.98.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.98.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.98.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.99.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.99.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.experts.99.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.gate.e_score_correction_bias": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.gate.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00054-of-00093.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00054-of-00093.safetensors", + "model.layers.54.input_layernorm.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.0.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.0.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.0.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.1.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.1.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.1.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.10.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.10.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.10.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.100.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.100.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.100.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.101.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.101.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.101.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.102.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.102.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.102.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.103.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.103.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.103.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.104.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.104.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.104.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.105.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.105.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.105.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.106.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.106.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.106.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.107.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.107.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.107.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.108.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.108.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.108.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.109.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.109.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.109.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.11.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.11.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.11.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.110.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.110.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.110.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.111.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.111.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.111.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.112.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.112.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.112.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.113.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.113.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.113.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.114.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.114.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.114.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.115.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.115.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.115.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.116.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.116.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.116.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.117.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.117.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.117.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.118.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.118.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.118.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.119.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.119.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.119.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.12.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.12.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.12.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.120.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.120.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.120.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.121.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.121.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.121.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.122.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.122.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.122.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.123.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.123.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.123.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.124.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.124.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.124.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.125.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.125.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.125.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.126.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.126.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.126.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.127.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.127.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.127.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.128.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.128.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.128.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.129.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.129.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.129.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.13.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.13.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.13.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.130.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.130.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.130.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.131.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.131.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.131.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.132.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.132.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.132.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.133.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.133.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.133.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.134.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.134.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.134.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.135.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.135.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.135.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.136.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.136.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.136.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.137.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.137.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.137.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.138.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.138.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.138.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.139.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.139.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.139.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.14.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.14.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.14.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.140.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.140.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.140.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.141.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.141.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.141.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.142.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.142.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.142.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.143.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.143.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.143.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.144.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.144.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.144.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.145.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.145.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.145.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.146.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.146.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.146.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.147.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.147.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.147.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.148.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.148.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.148.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.149.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.149.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.149.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.15.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.15.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.15.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.150.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.150.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.150.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.151.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.151.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.151.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.152.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.152.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.152.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.153.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.153.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.153.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.154.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.154.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.154.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.155.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.155.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.155.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.156.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.156.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.156.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.157.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.157.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.157.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.158.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.158.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.158.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.159.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.159.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.159.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.16.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.16.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.16.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.17.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.17.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.17.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.18.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.18.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.18.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.19.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.19.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.19.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.2.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.2.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.2.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.20.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.20.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.20.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.21.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.21.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.21.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.22.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.22.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.22.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.23.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.23.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.23.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.24.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.24.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.24.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.25.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.25.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.25.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.26.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.26.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.26.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.27.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.27.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.27.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.28.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.28.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.28.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.29.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.29.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.29.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.3.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.3.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.3.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.30.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.30.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.30.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.31.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.31.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.31.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.32.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.32.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.32.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.33.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.33.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.33.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.34.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.34.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.34.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.35.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.35.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.35.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.36.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.36.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.36.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.37.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.37.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.37.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.38.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.38.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.38.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.39.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.39.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.39.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.4.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.4.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.4.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.40.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.40.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.40.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.41.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.41.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.41.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.42.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.42.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.42.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.43.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.43.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.43.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.44.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.44.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.44.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.45.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.45.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.45.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.46.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.46.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.46.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.47.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.47.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.47.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.48.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.48.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.48.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.49.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.49.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.49.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.5.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.5.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.5.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.50.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.50.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.50.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.51.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.51.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.51.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.52.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.52.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.52.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.53.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.53.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.53.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.54.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.54.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.54.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.55.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.55.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.55.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.56.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.56.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.56.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.57.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.57.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.57.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.58.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.58.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.58.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.59.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.59.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.59.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.6.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.6.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.6.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.60.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.60.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.60.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.61.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.61.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.61.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.62.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.62.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.62.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.63.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.63.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.63.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.64.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.64.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.64.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.65.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.65.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.65.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.66.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.66.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.66.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.67.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.67.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.67.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.68.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.68.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.68.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.69.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.69.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.69.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.7.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.7.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.7.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.70.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.70.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.70.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.71.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.71.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.71.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.72.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.72.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.72.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.73.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.73.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.73.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.74.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.74.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.74.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.75.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.75.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.75.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.76.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.76.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.76.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.77.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.77.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.77.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.78.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.78.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.78.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.79.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.79.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.79.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.8.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.8.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.8.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.80.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.80.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.80.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.81.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.81.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.81.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.82.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.82.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.82.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.83.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.83.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.83.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.84.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.84.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.84.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.85.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.85.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.85.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.86.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.86.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.86.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.87.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.87.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.87.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.88.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.88.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.88.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.89.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.89.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.89.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.9.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.9.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.9.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.90.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.90.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.90.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.91.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.91.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.91.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.92.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.92.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.92.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.93.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.93.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.93.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.94.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.94.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.94.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.95.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.95.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.95.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.96.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.96.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.96.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.97.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.97.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.97.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.98.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.98.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.98.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.99.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.99.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.experts.99.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.gate.e_score_correction_bias": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.gate.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00055-of-00093.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00055-of-00093.safetensors", + "model.layers.55.input_layernorm.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.0.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.0.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.0.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.1.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.1.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.1.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.10.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.10.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.10.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.100.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.100.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.100.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.101.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.101.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.101.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.102.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.102.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.102.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.103.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.103.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.103.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.104.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.104.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.104.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.105.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.105.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.105.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.106.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.106.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.106.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.107.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.107.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.107.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.108.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.108.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.108.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.109.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.109.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.109.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.11.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.11.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.11.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.110.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.110.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.110.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.111.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.111.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.111.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.112.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.112.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.112.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.113.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.113.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.113.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.114.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.114.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.114.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.115.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.115.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.115.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.116.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.116.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.116.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.117.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.117.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.117.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.118.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.118.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.118.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.119.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.119.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.119.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.12.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.12.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.12.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.120.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.120.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.120.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.121.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.121.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.121.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.122.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.122.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.122.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.123.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.123.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.123.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.124.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.124.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.124.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.125.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.125.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.125.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.126.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.126.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.126.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.127.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.127.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.127.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.128.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.128.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.128.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.129.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.129.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.129.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.13.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.13.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.13.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.130.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.130.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.130.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.131.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.131.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.131.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.132.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.132.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.132.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.133.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.133.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.133.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.134.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.134.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.134.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.135.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.135.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.135.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.136.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.136.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.136.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.137.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.137.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.137.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.138.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.138.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.138.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.139.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.139.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.139.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.14.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.14.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.14.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.140.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.140.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.140.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.141.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.141.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.141.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.142.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.142.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.142.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.143.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.143.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.143.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.144.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.144.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.144.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.145.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.145.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.145.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.146.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.146.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.146.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.147.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.147.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.147.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.148.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.148.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.148.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.149.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.149.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.149.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.15.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.15.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.15.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.150.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.150.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.150.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.151.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.151.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.151.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.152.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.152.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.152.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.153.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.153.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.153.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.154.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.154.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.154.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.155.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.155.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.155.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.156.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.156.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.156.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.157.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.157.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.157.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.158.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.158.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.158.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.159.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.159.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.159.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.16.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.16.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.16.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.17.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.17.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.17.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.18.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.18.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.18.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.19.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.19.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.19.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.2.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.2.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.2.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.20.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.20.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.20.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.21.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.21.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.21.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.22.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.22.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.22.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.23.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.23.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.23.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.24.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.24.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.24.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.25.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.25.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.25.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.26.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.26.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.26.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.27.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.27.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.27.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.28.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.28.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.28.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.29.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.29.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.29.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.3.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.3.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.3.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.30.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.30.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.30.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.31.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.31.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.31.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.32.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.32.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.32.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.33.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.33.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.33.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.34.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.34.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.34.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.35.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.35.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.35.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.36.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.36.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.36.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.37.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.37.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.37.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.38.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.38.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.38.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.39.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.39.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.39.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.4.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.4.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.4.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.40.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.40.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.40.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.41.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.41.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.41.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.42.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.42.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.42.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.43.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.43.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.43.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.44.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.44.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.44.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.45.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.45.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.45.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.46.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.46.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.46.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.47.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.47.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.47.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.48.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.48.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.48.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.49.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.49.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.49.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.5.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.5.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.5.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.50.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.50.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.50.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.51.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.51.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.51.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.52.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.52.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.52.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.53.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.53.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.53.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.54.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.54.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.54.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.55.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.55.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.55.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.56.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.56.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.56.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.57.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.57.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.57.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.58.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.58.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.58.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.59.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.59.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.59.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.6.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.6.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.6.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.60.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.60.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.60.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.61.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.61.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.61.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.62.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.62.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.62.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.63.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.63.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.63.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.64.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.64.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.64.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.65.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.65.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.65.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.66.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.66.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.66.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.67.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.67.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.67.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.68.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.68.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.68.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.69.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.69.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.69.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.7.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.7.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.7.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.70.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.70.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.70.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.71.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.71.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.71.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.72.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.72.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.72.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.73.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.73.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.73.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.74.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.74.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.74.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.75.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.75.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.75.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.76.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.76.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.76.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.77.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.77.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.77.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.78.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.78.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.78.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.79.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.79.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.79.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.8.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.8.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.8.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.80.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.80.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.80.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.81.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.81.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.81.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.82.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.82.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.82.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.83.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.83.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.83.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.84.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.84.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.84.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.85.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.85.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.85.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.86.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.86.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.86.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.87.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.87.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.87.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.88.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.88.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.88.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.89.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.89.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.89.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.9.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.9.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.9.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.90.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.90.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.90.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.91.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.91.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.91.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.92.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.92.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.92.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.93.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.93.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.93.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.94.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.94.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.94.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.95.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.95.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.95.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.96.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.96.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.96.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.97.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.97.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.97.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.98.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.98.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.98.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.99.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.99.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.experts.99.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.gate.e_score_correction_bias": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.gate.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00056-of-00093.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00056-of-00093.safetensors", + "model.layers.56.input_layernorm.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.0.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.0.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.0.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.1.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.1.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.1.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.10.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.10.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.10.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.100.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.100.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.100.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.101.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.101.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.101.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.102.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.102.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.102.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.103.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.103.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.103.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.104.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.104.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.104.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.105.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.105.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.105.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.106.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.106.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.106.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.107.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.107.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.107.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.108.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.108.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.108.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.109.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.109.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.109.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.11.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.11.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.11.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.110.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.110.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.110.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.111.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.111.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.111.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.112.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.112.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.112.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.113.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.113.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.113.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.114.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.114.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.114.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.115.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.115.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.115.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.116.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.116.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.116.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.117.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.117.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.117.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.118.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.118.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.118.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.119.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.119.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.119.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.12.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.12.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.12.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.120.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.120.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.120.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.121.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.121.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.121.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.122.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.122.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.122.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.123.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.123.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.123.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.124.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.124.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.124.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.125.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.125.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.125.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.126.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.126.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.126.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.127.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.127.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.127.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.128.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.128.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.128.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.129.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.129.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.129.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.13.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.13.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.13.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.130.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.130.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.130.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.131.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.131.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.131.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.132.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.132.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.132.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.133.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.133.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.133.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.134.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.134.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.134.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.135.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.135.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.135.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.136.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.136.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.136.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.137.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.137.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.137.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.138.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.138.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.138.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.139.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.139.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.139.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.14.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.14.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.14.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.140.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.140.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.140.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.141.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.141.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.141.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.142.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.142.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.142.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.143.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.143.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.143.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.144.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.144.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.144.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.145.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.145.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.145.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.146.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.146.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.146.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.147.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.147.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.147.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.148.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.148.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.148.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.149.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.149.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.149.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.15.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.15.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.15.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.150.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.150.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.150.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.151.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.151.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.151.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.152.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.152.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.152.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.153.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.153.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.153.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.154.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.154.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.154.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.155.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.155.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.155.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.156.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.156.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.156.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.157.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.157.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.157.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.158.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.158.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.158.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.159.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.159.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.159.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.16.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.16.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.16.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.17.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.17.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.17.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.18.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.18.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.18.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.19.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.19.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.19.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.2.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.2.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.2.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.20.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.20.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.20.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.21.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.21.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.21.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.22.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.22.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.22.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.23.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.23.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.23.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.24.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.24.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.24.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.25.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.25.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.25.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.26.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.26.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.26.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.27.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.27.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.27.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.28.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.28.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.28.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.29.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.29.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.29.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.3.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.3.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.3.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.30.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.30.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.30.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.31.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.31.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.31.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.32.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.32.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.32.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.33.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.33.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.33.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.34.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.34.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.34.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.35.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.35.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.35.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.36.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.36.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.36.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.37.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.37.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.37.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.38.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.38.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.38.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.39.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.39.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.39.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.4.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.4.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.4.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.40.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.40.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.40.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.41.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.41.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.41.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.42.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.42.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.42.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.43.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.43.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.43.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.44.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.44.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.44.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.45.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.45.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.45.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.46.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.46.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.46.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.47.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.47.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.47.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.48.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.48.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.48.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.49.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.49.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.49.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.5.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.5.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.5.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.50.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.50.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.50.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.51.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.51.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.51.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.52.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.52.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.52.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.53.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.53.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.53.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.54.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.54.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.54.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.55.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.55.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.55.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.56.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.56.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.56.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.57.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.57.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.57.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.58.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.58.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.58.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.59.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.59.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.59.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.6.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.6.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.6.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.60.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.60.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.60.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.61.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.61.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.61.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.62.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.62.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.62.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.63.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.63.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.63.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.64.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.64.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.64.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.65.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.65.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.65.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.66.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.66.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.66.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.67.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.67.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.67.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.68.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.68.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.68.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.69.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.69.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.69.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.7.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.7.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.7.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.70.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.70.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.70.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.71.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.71.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.71.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.72.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.72.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.72.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.73.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.73.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.73.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.74.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.74.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.74.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.75.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.75.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.75.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.76.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.76.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.76.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.77.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.77.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.77.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.78.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.78.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.78.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.79.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.79.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.79.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.8.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.8.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.8.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.80.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.80.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.80.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.81.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.81.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.81.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.82.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.82.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.82.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.83.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.83.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.83.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.84.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.84.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.84.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.85.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.85.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.85.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.86.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.86.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.86.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.87.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.87.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.87.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.88.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.88.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.88.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.89.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.89.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.89.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.9.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.9.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.9.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.90.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.90.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.90.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.91.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.91.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.91.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.92.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.92.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.92.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.93.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.93.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.93.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.94.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.94.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.94.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.95.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.95.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.95.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.96.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.96.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.96.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.97.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.97.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.97.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.98.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.98.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.98.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.99.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.99.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.experts.99.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.gate.e_score_correction_bias": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.gate.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00057-of-00093.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00057-of-00093.safetensors", + "model.layers.57.input_layernorm.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.0.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.0.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.0.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.1.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.1.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.1.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.10.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.10.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.10.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.100.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.100.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.100.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.101.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.101.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.101.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.102.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.102.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.102.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.103.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.103.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.103.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.104.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.104.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.104.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.105.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.105.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.105.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.106.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.106.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.106.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.107.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.107.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.107.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.108.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.108.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.108.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.109.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.109.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.109.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.11.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.11.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.11.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.110.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.110.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.110.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.111.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.111.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.111.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.112.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.112.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.112.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.113.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.113.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.113.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.114.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.114.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.114.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.115.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.115.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.115.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.116.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.116.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.116.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.117.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.117.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.117.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.118.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.118.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.118.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.119.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.119.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.119.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.12.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.12.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.12.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.120.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.120.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.120.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.121.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.121.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.121.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.122.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.122.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.122.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.123.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.123.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.123.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.124.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.124.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.124.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.125.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.125.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.125.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.126.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.126.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.126.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.127.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.127.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.127.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.128.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.128.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.128.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.129.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.129.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.129.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.13.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.13.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.13.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.130.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.130.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.130.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.131.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.131.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.131.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.132.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.132.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.132.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.133.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.133.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.133.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.134.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.134.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.134.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.135.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.135.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.135.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.136.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.136.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.136.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.137.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.137.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.137.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.138.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.138.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.138.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.139.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.139.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.139.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.14.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.14.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.14.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.140.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.140.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.140.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.141.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.141.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.141.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.142.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.142.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.142.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.143.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.143.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.143.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.144.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.144.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.144.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.145.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.145.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.145.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.146.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.146.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.146.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.147.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.147.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.147.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.148.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.148.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.148.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.149.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.149.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.149.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.15.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.15.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.15.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.150.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.150.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.150.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.151.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.151.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.151.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.152.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.152.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.152.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.153.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.153.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.153.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.154.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.154.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.154.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.155.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.155.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.155.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.156.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.156.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.156.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.157.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.157.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.157.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.158.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.158.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.158.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.159.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.159.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.159.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.16.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.16.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.16.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.17.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.17.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.17.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.18.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.18.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.18.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.19.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.19.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.19.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.2.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.2.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.2.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.20.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.20.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.20.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.21.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.21.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.21.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.22.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.22.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.22.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.23.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.23.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.23.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.24.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.24.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.24.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.25.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.25.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.25.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.26.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.26.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.26.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.27.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.27.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.27.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.28.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.28.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.28.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.29.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.29.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.29.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.3.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.3.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.3.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.30.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.30.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.30.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.31.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.31.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.31.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.32.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.32.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.32.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.33.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.33.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.33.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.34.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.34.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.34.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.35.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.35.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.35.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.36.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.36.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.36.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.37.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.37.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.37.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.38.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.38.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.38.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.39.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.39.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.39.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.4.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.4.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.4.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.40.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.40.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.40.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.41.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.41.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.41.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.42.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.42.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.42.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.43.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.43.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.43.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.44.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.44.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.44.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.45.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.45.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.45.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.46.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.46.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.46.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.47.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.47.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.47.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.48.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.48.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.48.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.49.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.49.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.49.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.5.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.5.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.5.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.50.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.50.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.50.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.51.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.51.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.51.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.52.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.52.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.52.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.53.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.53.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.53.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.54.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.54.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.54.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.55.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.55.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.55.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.56.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.56.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.56.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.57.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.57.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.57.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.58.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.58.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.58.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.59.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.59.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.59.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.6.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.6.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.6.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.60.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.60.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.60.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.61.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.61.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.61.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.62.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.62.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.62.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.63.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.63.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.63.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.64.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.64.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.64.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.65.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.65.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.65.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.66.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.66.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.66.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.67.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.67.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.67.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.68.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.68.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.68.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.69.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.69.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.69.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.7.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.7.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.7.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.70.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.70.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.70.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.71.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.71.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.71.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.72.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.72.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.72.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.73.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.73.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.73.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.74.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.74.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.74.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.75.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.75.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.75.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.76.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.76.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.76.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.77.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.77.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.77.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.78.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.78.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.78.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.79.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.79.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.79.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.8.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.8.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.8.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.80.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.80.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.80.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.81.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.81.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.81.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.82.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.82.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.82.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.83.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.83.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.83.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.84.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.84.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.84.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.85.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.85.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.85.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.86.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.86.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.86.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.87.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.87.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.87.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.88.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.88.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.88.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.89.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.89.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.89.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.9.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.9.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.9.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.90.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.90.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.90.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.91.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.91.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.91.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.92.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.92.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.92.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.93.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.93.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.93.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.94.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.94.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.94.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.95.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.95.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.95.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.96.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.96.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.96.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.97.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.97.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.97.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.98.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.98.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.98.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.99.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.99.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.experts.99.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.gate.e_score_correction_bias": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.gate.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00058-of-00093.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00058-of-00093.safetensors", + "model.layers.58.input_layernorm.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.0.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.0.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.0.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.1.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.1.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.1.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.10.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.10.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.10.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.100.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.100.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.100.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.101.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.101.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.101.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.102.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.102.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.102.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.103.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.103.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.103.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.104.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.104.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.104.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.105.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.105.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.105.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.106.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.106.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.106.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.107.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.107.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.107.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.108.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.108.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.108.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.109.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.109.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.109.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.11.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.11.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.11.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.110.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.110.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.110.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.111.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.111.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.111.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.112.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.112.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.112.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.113.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.113.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.113.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.114.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.114.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.114.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.115.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.115.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.115.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.116.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.116.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.116.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.117.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.117.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.117.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.118.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.118.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.118.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.119.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.119.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.119.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.12.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.12.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.12.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.120.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.120.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.120.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.121.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.121.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.121.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.122.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.122.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.122.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.123.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.123.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.123.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.124.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.124.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.124.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.125.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.125.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.125.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.126.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.126.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.126.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.127.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.127.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.127.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.128.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.128.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.128.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.129.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.129.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.129.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.13.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.13.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.13.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.130.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.130.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.130.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.131.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.131.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.131.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.132.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.132.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.132.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.133.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.133.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.133.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.134.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.134.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.134.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.135.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.135.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.135.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.136.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.136.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.136.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.137.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.137.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.137.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.138.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.138.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.138.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.139.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.139.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.139.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.14.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.14.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.14.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.140.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.140.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.140.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.141.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.141.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.141.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.142.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.142.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.142.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.143.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.143.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.143.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.144.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.144.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.144.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.145.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.145.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.145.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.146.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.146.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.146.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.147.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.147.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.147.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.148.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.148.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.148.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.149.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.149.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.149.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.15.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.15.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.15.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.150.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.150.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.150.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.151.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.151.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.151.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.152.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.152.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.152.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.153.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.153.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.153.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.154.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.154.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.154.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.155.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.155.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.155.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.156.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.156.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.156.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.157.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.157.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.157.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.158.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.158.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.158.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.159.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.159.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.159.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.16.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.16.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.16.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.17.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.17.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.17.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.18.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.18.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.18.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.19.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.19.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.19.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.2.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.2.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.2.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.20.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.20.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.20.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.21.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.21.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.21.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.22.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.22.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.22.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.23.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.23.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.23.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.24.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.24.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.24.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.25.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.25.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.25.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.26.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.26.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.26.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.27.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.27.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.27.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.28.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.28.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.28.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.29.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.29.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.29.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.3.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.3.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.3.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.30.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.30.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.30.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.31.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.31.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.31.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.32.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.32.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.32.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.33.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.33.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.33.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.34.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.34.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.34.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.35.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.35.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.35.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.36.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.36.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.36.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.37.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.37.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.37.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.38.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.38.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.38.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.39.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.39.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.39.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.4.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.4.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.4.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.40.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.40.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.40.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.41.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.41.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.41.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.42.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.42.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.42.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.43.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.43.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.43.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.44.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.44.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.44.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.45.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.45.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.45.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.46.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.46.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.46.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.47.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.47.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.47.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.48.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.48.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.48.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.49.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.49.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.49.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.5.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.5.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.5.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.50.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.50.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.50.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.51.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.51.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.51.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.52.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.52.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.52.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.53.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.53.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.53.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.54.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.54.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.54.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.55.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.55.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.55.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.56.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.56.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.56.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.57.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.57.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.57.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.58.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.58.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.58.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.59.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.59.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.59.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.6.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.6.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.6.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.60.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.60.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.60.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.61.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.61.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.61.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.62.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.62.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.62.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.63.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.63.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.63.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.64.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.64.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.64.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.65.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.65.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.65.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.66.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.66.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.66.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.67.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.67.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.67.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.68.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.68.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.68.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.69.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.69.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.69.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.7.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.7.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.7.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.70.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.70.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.70.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.71.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.71.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.71.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.72.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.72.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.72.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.73.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.73.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.73.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.74.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.74.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.74.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.75.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.75.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.75.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.76.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.76.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.76.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.77.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.77.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.77.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.78.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.78.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.78.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.79.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.79.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.79.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.8.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.8.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.8.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.80.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.80.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.80.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.81.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.81.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.81.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.82.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.82.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.82.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.83.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.83.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.83.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.84.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.84.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.84.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.85.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.85.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.85.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.86.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.86.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.86.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.87.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.87.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.87.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.88.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.88.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.88.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.89.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.89.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.89.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.9.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.9.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.9.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.90.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.90.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.90.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.91.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.91.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.91.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.92.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.92.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.92.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.93.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.93.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.93.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.94.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.94.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.94.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.95.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.95.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.95.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.96.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.96.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.96.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.97.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.97.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.97.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.98.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.98.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.98.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.99.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.99.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.experts.99.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.gate.e_score_correction_bias": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.gate.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00059-of-00093.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00059-of-00093.safetensors", + "model.layers.59.input_layernorm.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.0.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.0.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.0.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.1.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.1.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.1.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.10.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.10.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.10.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.100.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.100.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.100.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.101.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.101.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.101.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.102.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.102.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.102.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.103.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.103.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.103.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.104.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.104.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.104.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.105.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.105.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.105.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.106.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.106.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.106.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.107.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.107.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.107.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.108.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.108.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.108.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.109.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.109.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.109.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.11.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.11.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.11.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.110.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.110.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.110.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.111.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.111.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.111.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.112.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.112.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.112.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.113.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.113.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.113.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.114.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.114.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.114.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.115.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.115.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.115.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.116.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.116.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.116.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.117.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.117.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.117.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.118.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.118.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.118.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.119.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.119.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.119.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.12.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.12.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.12.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.120.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.120.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.120.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.121.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.121.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.121.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.122.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.122.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.122.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.123.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.123.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.123.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.124.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.124.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.124.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.125.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.125.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.125.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.126.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.126.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.126.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.127.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.127.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.127.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.128.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.128.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.128.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.129.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.129.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.129.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.13.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.13.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.13.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.130.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.130.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.130.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.131.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.131.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.131.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.132.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.132.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.132.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.133.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.133.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.133.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.134.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.134.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.134.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.135.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.135.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.135.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.136.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.136.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.136.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.137.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.137.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.137.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.138.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.138.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.138.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.139.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.139.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.139.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.14.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.14.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.14.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.140.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.140.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.140.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.141.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.141.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.141.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.142.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.142.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.142.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.143.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.143.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.143.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.144.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.144.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.144.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.145.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.145.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.145.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.146.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.146.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.146.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.147.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.147.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.147.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.148.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.148.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.148.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.149.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.149.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.149.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.15.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.15.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.15.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.150.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.150.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.150.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.151.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.151.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.151.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.152.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.152.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.152.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.153.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.153.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.153.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.154.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.154.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.154.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.155.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.155.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.155.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.156.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.156.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.156.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.157.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.157.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.157.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.158.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.158.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.158.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.159.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.159.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.159.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.16.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.16.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.16.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.17.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.17.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.17.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.18.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.18.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.18.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.19.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.19.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.19.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.2.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.2.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.2.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.20.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.20.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.20.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.21.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.21.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.21.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.22.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.22.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.22.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.23.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.23.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.23.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.24.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.24.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.24.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.25.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.25.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.25.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.26.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.26.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.26.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.27.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.27.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.27.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.28.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.28.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.28.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.29.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.29.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.29.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.3.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.3.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.3.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.30.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.30.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.30.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.31.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.31.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.31.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.32.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.32.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.32.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.33.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.33.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.33.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.34.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.34.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.34.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.35.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.35.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.35.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.36.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.36.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.36.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.37.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.37.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.37.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.38.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.38.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.38.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.39.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.39.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.39.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.4.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.4.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.4.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.40.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.40.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.40.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.41.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.41.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.41.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.42.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.42.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.42.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.43.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.43.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.43.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.44.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.44.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.44.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.45.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.45.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.45.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.46.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.46.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.46.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.47.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.47.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.47.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.48.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.48.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.48.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.49.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.49.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.49.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.5.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.5.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.5.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.50.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.50.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.50.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.51.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.51.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.51.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.52.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.52.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.52.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.53.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.53.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.53.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.54.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.54.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.54.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.55.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.55.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.55.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.56.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.56.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.56.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.57.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.57.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.57.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.58.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.58.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.58.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.59.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.59.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.59.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.6.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.6.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.6.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.60.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.60.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.60.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.61.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.61.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.61.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.62.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.62.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.62.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.63.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.63.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.63.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.64.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.64.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.64.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.65.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.65.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.65.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.66.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.66.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.66.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.67.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.67.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.67.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.68.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.68.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.68.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.69.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.69.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.69.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.7.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.7.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.7.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.70.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.70.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.70.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.71.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.71.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.71.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.72.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.72.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.72.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.73.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.73.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.73.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.74.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.74.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.74.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.75.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.75.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.75.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.76.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.76.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.76.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.77.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.77.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.77.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.78.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.78.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.78.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.79.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.79.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.79.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.8.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.8.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.8.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.80.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.80.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.80.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.81.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.81.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.81.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.82.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.82.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.82.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.83.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.83.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.83.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.84.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.84.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.84.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.85.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.85.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.85.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.86.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.86.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.86.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.87.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.87.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.87.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.88.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.88.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.88.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.89.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.89.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.89.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.9.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.9.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.9.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.90.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.90.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.90.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.91.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.91.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.91.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.92.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.92.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.92.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.93.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.93.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.93.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.94.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.94.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.94.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.95.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.95.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.95.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.96.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.96.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.96.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.97.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.97.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.97.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.98.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.98.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.98.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.99.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.99.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.experts.99.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.gate.e_score_correction_bias": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.gate.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00060-of-00093.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00060-of-00093.safetensors", + "model.layers.60.input_layernorm.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.0.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.0.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.0.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.1.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.1.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.1.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.10.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.10.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.10.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.100.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.100.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.100.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.101.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.101.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.101.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.102.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.102.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.102.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.103.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.103.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.103.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.104.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.104.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.104.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.105.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.105.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.105.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.106.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.106.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.106.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.107.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.107.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.107.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.108.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.108.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.108.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.109.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.109.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.109.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.11.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.11.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.11.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.110.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.110.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.110.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.111.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.111.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.111.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.112.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.112.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.112.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.113.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.113.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.113.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.114.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.114.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.114.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.115.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.115.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.115.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.116.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.116.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.116.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.117.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.117.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.117.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.118.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.118.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.118.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.119.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.119.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.119.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.12.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.12.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.12.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.120.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.120.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.120.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.121.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.121.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.121.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.122.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.122.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.122.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.123.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.123.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.123.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.124.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.124.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.124.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.125.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.125.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.125.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.126.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.126.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.126.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.127.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.127.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.127.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.128.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.128.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.128.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.129.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.129.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.129.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.13.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.13.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.13.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.130.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.130.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.130.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.131.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.131.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.131.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.132.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.132.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.132.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.133.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.133.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.133.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.134.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.134.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.134.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.135.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.135.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.135.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.136.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.136.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.136.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.137.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.137.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.137.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.138.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.138.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.138.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.139.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.139.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.139.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.14.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.14.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.14.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.140.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.140.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.140.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.141.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.141.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.141.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.142.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.142.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.142.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.143.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.143.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.143.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.144.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.144.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.144.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.145.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.145.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.145.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.146.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.146.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.146.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.147.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.147.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.147.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.148.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.148.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.148.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.149.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.149.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.149.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.15.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.15.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.15.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.150.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.150.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.150.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.151.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.151.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.151.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.152.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.152.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.152.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.153.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.153.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.153.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.154.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.154.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.154.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.155.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.155.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.155.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.156.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.156.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.156.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.157.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.157.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.157.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.158.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.158.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.158.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.159.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.159.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.159.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.16.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.16.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.16.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.17.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.17.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.17.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.18.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.18.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.18.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.19.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.19.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.19.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.2.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.2.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.2.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.20.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.20.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.20.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.21.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.21.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.21.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.22.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.22.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.22.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.23.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.23.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.23.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.24.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.24.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.24.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.25.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.25.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.25.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.26.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.26.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.26.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.27.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.27.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.27.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.28.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.28.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.28.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.29.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.29.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.29.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.3.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.3.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.3.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.30.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.30.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.30.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.31.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.31.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.31.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.32.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.32.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.32.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.33.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.33.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.33.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.34.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.34.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.34.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.35.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.35.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.35.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.36.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.36.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.36.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.37.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.37.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.37.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.38.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.38.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.38.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.39.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.39.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.39.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.4.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.4.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.4.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.40.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.40.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.40.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.41.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.41.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.41.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.42.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.42.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.42.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.43.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.43.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.43.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.44.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.44.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.44.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.45.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.45.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.45.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.46.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.46.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.46.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.47.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.47.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.47.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.48.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.48.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.48.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.49.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.49.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.49.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.5.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.5.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.5.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.50.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.50.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.50.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.51.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.51.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.51.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.52.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.52.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.52.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.53.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.53.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.53.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.54.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.54.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.54.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.55.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.55.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.55.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.56.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.56.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.56.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.57.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.57.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.57.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.58.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.58.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.58.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.59.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.59.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.59.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.6.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.6.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.6.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.60.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.60.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.60.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.61.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.61.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.61.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.62.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.62.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.62.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.63.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.63.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.63.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.64.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.64.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.64.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.65.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.65.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.65.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.66.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.66.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.66.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.67.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.67.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.67.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.68.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.68.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.68.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.69.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.69.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.69.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.7.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.7.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.7.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.70.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.70.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.70.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.71.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.71.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.71.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.72.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.72.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.72.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.73.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.73.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.73.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.74.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.74.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.74.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.75.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.75.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.75.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.76.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.76.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.76.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.77.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.77.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.77.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.78.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.78.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.78.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.79.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.79.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.79.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.8.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.8.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.8.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.80.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.80.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.80.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.81.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.81.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.81.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.82.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.82.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.82.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.83.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.83.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.83.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.84.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.84.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.84.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.85.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.85.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.85.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.86.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.86.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.86.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.87.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.87.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.87.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.88.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.88.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.88.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.89.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.89.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.89.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.9.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.9.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.9.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.90.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.90.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.90.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.91.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.91.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.91.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.92.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.92.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.92.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.93.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.93.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.93.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.94.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.94.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.94.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.95.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.95.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.95.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.96.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.96.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.96.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.97.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.97.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.97.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.98.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.98.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.98.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.99.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.99.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.experts.99.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.gate.e_score_correction_bias": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.gate.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00061-of-00093.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00061-of-00093.safetensors", + "model.layers.61.input_layernorm.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.0.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.0.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.0.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.1.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.1.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.1.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.10.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.10.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.10.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.100.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.100.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.100.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.101.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.101.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.101.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.102.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.102.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.102.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.103.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.103.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.103.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.104.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.104.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.104.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.105.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.105.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.105.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.106.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.106.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.106.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.107.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.107.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.107.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.108.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.108.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.108.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.109.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.109.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.109.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.11.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.11.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.11.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.110.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.110.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.110.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.111.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.111.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.111.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.112.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.112.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.112.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.113.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.113.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.113.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.114.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.114.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.114.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.115.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.115.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.115.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.116.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.116.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.116.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.117.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.117.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.117.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.118.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.118.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.118.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.119.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.119.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.119.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.12.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.12.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.12.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.120.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.120.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.120.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.121.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.121.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.121.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.122.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.122.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.122.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.123.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.123.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.123.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.124.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.124.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.124.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.125.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.125.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.125.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.126.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.126.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.126.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.127.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.127.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.127.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.128.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.128.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.128.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.129.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.129.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.129.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.13.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.13.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.13.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.130.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.130.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.130.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.131.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.131.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.131.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.132.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.132.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.132.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.133.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.133.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.133.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.134.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.134.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.134.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.135.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.135.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.135.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.136.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.136.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.136.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.137.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.137.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.137.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.138.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.138.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.138.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.139.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.139.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.139.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.14.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.14.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.14.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.140.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.140.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.140.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.141.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.141.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.141.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.142.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.142.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.142.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.143.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.143.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.143.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.144.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.144.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.144.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.145.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.145.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.145.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.146.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.146.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.146.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.147.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.147.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.147.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.148.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.148.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.148.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.149.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.149.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.149.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.15.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.15.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.15.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.150.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.150.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.150.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.151.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.151.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.151.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.152.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.152.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.152.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.153.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.153.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.153.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.154.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.154.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.154.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.155.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.155.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.155.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.156.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.156.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.156.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.157.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.157.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.157.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.158.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.158.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.158.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.159.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.159.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.159.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.16.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.16.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.16.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.17.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.17.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.17.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.18.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.18.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.18.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.19.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.19.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.19.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.2.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.2.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.2.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.20.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.20.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.20.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.21.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.21.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.21.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.22.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.22.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.22.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.23.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.23.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.23.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.24.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.24.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.24.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.25.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.25.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.25.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.26.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.26.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.26.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.27.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.27.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.27.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.28.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.28.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.28.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.29.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.29.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.29.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.3.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.3.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.3.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.30.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.30.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.30.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.31.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.31.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.31.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.32.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.32.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.32.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.33.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.33.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.33.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.34.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.34.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.34.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.35.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.35.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.35.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.36.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.36.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.36.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.37.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.37.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.37.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.38.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.38.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.38.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.39.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.39.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.39.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.4.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.4.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.4.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.40.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.40.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.40.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.41.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.41.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.41.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.42.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.42.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.42.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.43.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.43.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.43.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.44.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.44.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.44.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.45.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.45.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.45.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.46.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.46.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.46.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.47.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.47.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.47.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.48.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.48.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.48.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.49.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.49.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.49.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.5.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.5.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.5.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.50.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.50.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.50.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.51.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.51.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.51.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.52.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.52.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.52.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.53.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.53.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.53.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.54.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.54.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.54.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.55.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.55.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.55.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.56.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.56.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.56.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.57.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.57.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.57.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.58.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.58.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.58.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.59.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.59.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.59.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.6.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.6.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.6.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.60.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.60.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.60.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.61.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.61.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.61.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.62.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.62.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.62.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.63.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.63.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.63.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.64.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.64.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.64.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.65.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.65.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.65.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.66.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.66.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.66.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.67.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.67.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.67.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.68.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.68.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.68.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.69.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.69.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.69.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.7.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.7.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.7.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.70.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.70.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.70.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.71.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.71.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.71.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.72.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.72.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.72.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.73.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.73.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.73.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.74.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.74.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.74.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.75.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.75.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.75.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.76.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.76.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.76.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.77.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.77.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.77.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.78.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.78.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.78.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.79.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.79.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.79.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.8.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.8.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.8.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.80.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.80.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.80.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.81.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.81.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.81.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.82.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.82.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.82.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.83.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.83.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.83.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.84.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.84.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.84.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.85.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.85.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.85.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.86.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.86.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.86.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.87.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.87.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.87.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.88.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.88.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.88.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.89.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.89.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.89.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.9.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.9.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.9.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.90.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.90.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.90.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.91.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.91.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.91.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.92.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.92.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.92.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.93.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.93.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.93.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.94.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.94.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.94.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.95.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.95.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.95.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.96.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.96.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.96.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.97.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.97.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.97.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.98.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.98.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.98.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.99.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.99.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.experts.99.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.gate.e_score_correction_bias": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.gate.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00062-of-00093.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00062-of-00093.safetensors", + "model.layers.62.input_layernorm.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.0.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.0.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.0.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.1.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.1.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.1.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.10.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.10.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.10.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.100.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.100.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.100.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.101.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.101.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.101.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.102.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.102.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.102.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.103.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.103.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.103.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.104.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.104.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.104.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.105.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.105.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.105.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.106.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.106.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.106.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.107.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.107.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.107.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.108.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.108.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.108.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.109.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.109.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.109.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.11.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.11.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.11.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.110.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.110.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.110.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.111.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.111.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.111.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.112.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.112.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.112.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.113.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.113.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.113.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.114.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.114.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.114.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.115.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.115.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.115.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.116.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.116.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.116.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.117.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.117.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.117.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.118.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.118.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.118.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.119.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.119.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.119.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.12.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.12.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.12.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.120.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.120.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.120.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.121.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.121.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.121.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.122.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.122.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.122.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.123.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.123.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.123.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.124.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.124.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.124.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.125.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.125.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.125.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.126.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.126.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.126.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.127.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.127.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.127.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.128.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.128.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.128.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.129.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.129.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.129.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.13.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.13.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.13.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.130.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.130.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.130.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.131.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.131.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.131.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.132.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.132.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.132.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.133.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.133.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.133.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.134.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.134.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.134.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.135.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.135.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.135.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.136.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.136.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.136.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.137.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.137.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.137.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.138.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.138.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.138.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.139.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.139.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.139.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.14.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.14.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.14.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.140.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.140.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.140.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.141.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.141.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.141.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.142.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.142.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.142.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.143.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.143.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.143.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.144.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.144.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.144.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.145.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.145.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.145.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.146.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.146.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.146.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.147.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.147.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.147.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.148.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.148.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.148.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.149.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.149.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.149.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.15.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.15.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.15.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.150.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.150.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.150.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.151.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.151.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.151.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.152.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.152.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.152.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.153.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.153.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.153.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.154.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.154.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.154.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.155.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.155.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.155.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.156.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.156.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.156.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.157.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.157.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.157.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.158.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.158.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.158.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.159.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.159.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.159.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.16.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.16.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.16.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.17.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.17.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.17.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.18.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.18.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.18.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.19.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.19.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.19.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.2.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.2.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.2.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.20.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.20.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.20.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.21.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.21.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.21.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.22.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.22.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.22.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.23.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.23.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.23.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.24.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.24.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.24.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.25.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.25.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.25.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.26.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.26.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.26.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.27.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.27.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.27.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.28.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.28.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.28.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.29.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.29.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.29.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.3.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.3.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.3.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.30.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.30.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.30.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.31.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.31.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.31.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.32.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.32.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.32.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.33.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.33.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.33.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.34.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.34.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.34.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.35.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.35.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.35.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.36.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.36.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.36.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.37.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.37.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.37.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.38.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.38.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.38.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.39.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.39.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.39.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.4.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.4.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.4.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.40.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.40.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.40.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.41.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.41.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.41.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.42.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.42.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.42.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.43.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.43.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.43.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.44.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.44.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.44.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.45.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.45.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.45.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.46.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.46.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.46.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.47.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.47.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.47.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.48.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.48.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.48.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.49.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.49.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.49.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.5.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.5.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.5.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.50.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.50.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.50.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.51.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.51.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.51.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.52.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.52.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.52.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.53.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.53.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.53.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.54.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.54.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.54.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.55.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.55.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.55.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.56.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.56.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.56.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.57.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.57.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.57.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.58.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.58.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.58.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.59.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.59.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.59.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.6.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.6.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.6.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.60.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.60.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.60.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.61.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.61.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.61.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.62.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.62.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.62.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.63.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.63.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.63.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.64.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.64.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.64.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.65.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.65.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.65.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.66.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.66.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.66.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.67.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.67.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.67.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.68.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.68.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.68.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.69.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.69.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.69.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.7.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.7.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.7.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.70.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.70.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.70.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.71.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.71.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.71.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.72.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.72.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.72.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.73.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.73.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.73.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.74.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.74.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.74.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.75.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.75.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.75.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.76.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.76.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.76.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.77.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.77.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.77.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.78.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.78.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.78.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.79.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.79.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.79.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.8.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.8.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.8.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.80.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.80.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.80.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.81.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.81.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.81.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.82.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.82.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.82.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.83.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.83.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.83.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.84.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.84.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.84.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.85.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.85.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.85.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.86.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.86.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.86.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.87.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.87.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.87.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.88.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.88.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.88.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.89.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.89.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.89.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.9.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.9.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.9.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.90.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.90.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.90.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.91.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.91.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.91.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.92.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.92.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.92.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.93.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.93.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.93.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.94.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.94.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.94.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.95.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.95.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.95.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.96.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.96.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.96.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.97.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.97.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.97.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.98.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.98.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.98.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.99.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.99.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.experts.99.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.gate.e_score_correction_bias": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.gate.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00063-of-00093.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00063-of-00093.safetensors", + "model.layers.63.input_layernorm.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.0.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.0.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.0.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.1.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.1.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.1.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.10.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.10.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.10.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.100.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.100.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.100.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.101.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.101.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.101.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.102.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.102.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.102.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.103.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.103.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.103.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.104.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.104.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.104.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.105.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.105.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.105.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.106.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.106.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.106.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.107.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.107.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.107.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.108.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.108.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.108.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.109.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.109.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.109.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.11.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.11.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.11.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.110.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.110.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.110.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.111.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.111.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.111.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.112.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.112.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.112.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.113.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.113.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.113.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.114.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.114.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.114.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.115.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.115.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.115.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.116.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.116.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.116.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.117.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.117.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.117.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.118.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.118.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.118.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.119.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.119.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.119.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.12.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.12.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.12.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.120.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.120.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.120.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.121.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.121.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.121.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.122.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.122.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.122.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.123.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.123.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.123.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.124.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.124.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.124.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.125.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.125.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.125.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.126.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.126.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.126.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.127.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.127.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.127.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.128.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.128.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.128.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.129.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.129.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.129.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.13.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.13.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.13.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.130.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.130.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.130.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.131.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.131.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.131.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.132.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.132.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.132.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.133.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.133.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.133.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.134.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.134.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.134.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.135.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.135.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.135.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.136.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.136.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.136.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.137.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.137.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.137.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.138.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.138.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.138.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.139.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.139.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.139.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.14.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.14.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.14.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.140.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.140.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.140.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.141.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.141.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.141.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.142.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.142.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.142.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.143.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.143.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.143.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.144.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.144.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.144.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.145.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.145.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.145.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.146.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.146.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.146.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.147.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.147.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.147.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.148.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.148.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.148.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.149.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.149.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.149.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.15.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.15.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.15.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.150.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.150.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.150.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.151.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.151.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.151.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.152.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.152.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.152.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.153.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.153.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.153.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.154.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.154.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.154.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.155.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.155.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.155.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.156.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.156.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.156.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.157.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.157.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.157.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.158.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.158.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.158.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.159.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.159.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.159.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.16.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.16.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.16.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.17.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.17.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.17.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.18.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.18.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.18.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.19.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.19.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.19.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.2.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.2.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.2.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.20.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.20.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.20.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.21.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.21.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.21.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.22.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.22.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.22.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.23.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.23.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.23.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.24.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.24.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.24.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.25.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.25.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.25.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.26.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.26.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.26.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.27.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.27.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.27.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.28.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.28.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.28.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.29.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.29.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.29.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.3.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.3.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.3.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.30.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.30.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.30.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.31.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.31.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.31.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.32.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.32.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.32.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.33.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.33.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.33.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.34.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.34.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.34.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.35.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.35.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.35.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.36.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.36.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.36.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.37.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.37.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.37.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.38.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.38.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.38.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.39.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.39.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.39.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.4.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.4.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.4.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.40.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.40.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.40.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.41.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.41.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.41.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.42.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.42.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.42.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.43.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.43.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.43.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.44.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.44.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.44.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.45.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.45.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.45.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.46.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.46.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.46.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.47.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.47.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.47.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.48.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.48.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.48.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.49.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.49.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.49.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.5.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.5.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.5.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.50.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.50.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.50.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.51.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.51.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.51.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.52.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.52.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.52.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.53.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.53.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.53.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.54.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.54.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.54.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.55.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.55.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.55.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.56.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.56.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.56.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.57.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.57.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.57.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.58.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.58.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.58.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.59.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.59.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.59.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.6.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.6.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.6.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.60.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.60.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.60.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.61.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.61.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.61.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.62.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.62.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.62.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.63.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.63.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.63.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.64.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.64.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.64.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.65.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.65.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.65.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.66.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.66.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.66.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.67.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.67.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.67.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.68.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.68.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.68.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.69.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.69.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.69.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.7.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.7.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.7.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.70.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.70.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.70.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.71.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.71.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.71.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.72.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.72.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.72.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.73.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.73.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.73.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.74.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.74.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.74.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.75.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.75.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.75.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.76.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.76.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.76.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.77.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.77.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.77.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.78.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.78.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.78.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.79.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.79.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.79.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.8.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.8.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.8.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.80.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.80.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.80.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.81.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.81.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.81.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.82.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.82.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.82.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.83.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.83.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.83.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.84.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.84.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.84.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.85.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.85.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.85.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.86.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.86.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.86.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.87.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.87.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.87.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.88.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.88.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.88.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.89.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.89.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.89.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.9.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.9.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.9.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.90.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.90.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.90.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.91.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.91.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.91.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.92.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.92.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.92.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.93.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.93.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.93.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.94.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.94.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.94.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.95.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.95.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.95.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.96.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.96.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.96.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.97.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.97.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.97.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.98.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.98.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.98.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.99.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.99.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.experts.99.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.gate.e_score_correction_bias": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.gate.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00064-of-00093.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00064-of-00093.safetensors", + "model.layers.64.input_layernorm.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.0.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.0.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.0.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.1.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.1.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.1.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.10.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.10.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.10.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.100.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.100.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.100.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.101.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.101.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.101.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.102.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.102.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.102.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.103.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.103.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.103.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.104.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.104.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.104.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.105.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.105.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.105.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.106.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.106.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.106.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.107.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.107.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.107.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.108.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.108.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.108.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.109.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.109.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.109.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.11.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.11.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.11.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.110.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.110.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.110.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.111.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.111.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.111.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.112.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.112.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.112.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.113.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.113.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.113.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.114.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.114.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.114.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.115.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.115.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.115.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.116.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.116.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.116.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.117.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.117.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.117.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.118.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.118.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.118.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.119.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.119.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.119.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.12.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.12.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.12.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.120.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.120.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.120.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.121.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.121.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.121.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.122.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.122.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.122.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.123.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.123.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.123.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.124.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.124.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.124.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.125.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.125.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.125.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.126.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.126.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.126.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.127.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.127.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.127.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.128.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.128.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.128.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.129.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.129.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.129.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.13.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.13.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.13.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.130.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.130.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.130.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.131.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.131.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.131.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.132.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.132.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.132.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.133.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.133.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.133.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.134.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.134.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.134.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.135.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.135.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.135.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.136.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.136.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.136.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.137.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.137.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.137.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.138.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.138.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.138.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.139.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.139.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.139.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.14.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.14.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.14.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.140.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.140.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.140.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.141.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.141.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.141.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.142.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.142.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.142.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.143.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.143.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.143.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.144.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.144.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.144.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.145.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.145.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.145.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.146.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.146.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.146.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.147.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.147.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.147.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.148.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.148.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.148.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.149.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.149.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.149.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.15.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.15.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.15.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.150.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.150.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.150.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.151.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.151.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.151.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.152.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.152.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.152.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.153.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.153.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.153.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.154.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.154.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.154.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.155.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.155.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.155.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.156.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.156.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.156.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.157.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.157.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.157.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.158.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.158.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.158.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.159.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.159.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.159.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.16.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.16.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.16.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.17.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.17.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.17.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.18.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.18.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.18.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.19.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.19.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.19.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.2.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.2.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.2.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.20.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.20.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.20.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.21.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.21.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.21.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.22.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.22.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.22.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.23.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.23.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.23.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.24.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.24.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.24.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.25.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.25.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.25.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.26.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.26.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.26.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.27.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.27.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.27.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.28.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.28.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.28.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.29.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.29.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.29.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.3.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.3.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.3.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.30.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.30.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.30.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.31.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.31.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.31.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.32.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.32.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.32.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.33.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.33.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.33.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.34.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.34.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.34.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.35.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.35.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.35.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.36.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.36.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.36.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.37.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.37.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.37.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.38.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.38.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.38.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.39.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.39.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.39.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.4.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.4.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.4.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.40.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.40.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.40.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.41.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.41.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.41.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.42.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.42.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.42.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.43.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.43.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.43.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.44.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.44.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.44.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.45.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.45.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.45.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.46.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.46.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.46.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.47.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.47.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.47.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.48.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.48.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.48.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.49.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.49.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.49.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.5.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.5.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.5.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.50.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.50.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.50.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.51.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.51.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.51.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.52.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.52.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.52.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.53.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.53.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.53.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.54.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.54.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.54.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.55.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.55.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.55.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.56.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.56.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.56.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.57.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.57.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.57.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.58.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.58.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.58.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.59.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.59.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.59.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.6.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.6.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.6.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.60.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.60.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.60.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.61.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.61.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.61.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.62.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.62.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.62.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.63.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.63.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.63.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.64.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.64.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.64.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.65.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.65.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.65.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.66.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.66.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.66.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.67.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.67.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.67.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.68.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.68.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.68.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.69.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.69.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.69.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.7.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.7.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.7.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.70.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.70.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.70.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.71.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.71.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.71.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.72.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.72.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.72.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.73.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.73.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.73.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.74.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.74.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.74.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.75.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.75.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.75.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.76.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.76.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.76.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.77.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.77.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.77.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.78.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.78.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.78.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.79.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.79.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.79.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.8.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.8.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.8.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.80.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.80.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.80.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.81.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.81.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.81.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.82.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.82.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.82.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.83.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.83.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.83.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.84.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.84.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.84.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.85.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.85.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.85.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.86.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.86.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.86.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.87.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.87.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.87.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.88.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.88.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.88.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.89.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.89.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.89.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.9.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.9.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.9.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.90.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.90.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.90.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.91.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.91.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.91.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.92.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.92.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.92.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.93.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.93.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.93.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.94.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.94.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.94.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.95.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.95.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.95.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.96.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.96.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.96.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.97.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.97.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.97.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.98.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.98.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.98.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.99.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.99.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.experts.99.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.gate.e_score_correction_bias": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.gate.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.k_norm.weight": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.k_proj.bias": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.q_norm.weight": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.q_proj.bias": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.v_proj.bias": "model-00065-of-00093.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00065-of-00093.safetensors", + "model.layers.65.input_layernorm.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.0.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.0.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.0.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.1.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.1.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.1.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.10.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.10.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.10.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.100.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.100.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.100.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.101.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.101.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.101.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.102.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.102.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.102.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.103.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.103.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.103.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.104.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.104.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.104.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.105.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.105.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.105.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.106.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.106.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.106.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.107.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.107.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.107.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.108.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.108.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.108.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.109.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.109.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.109.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.11.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.11.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.11.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.110.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.110.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.110.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.111.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.111.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.111.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.112.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.112.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.112.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.113.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.113.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.113.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.114.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.114.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.114.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.115.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.115.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.115.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.116.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.116.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.116.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.117.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.117.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.117.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.118.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.118.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.118.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.119.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.119.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.119.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.12.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.12.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.12.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.120.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.120.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.120.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.121.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.121.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.121.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.122.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.122.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.122.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.123.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.123.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.123.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.124.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.124.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.124.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.125.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.125.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.125.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.126.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.126.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.126.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.127.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.127.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.127.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.128.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.128.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.128.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.129.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.129.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.129.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.13.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.13.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.13.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.130.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.130.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.130.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.131.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.131.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.131.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.132.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.132.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.132.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.133.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.133.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.133.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.134.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.134.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.134.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.135.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.135.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.135.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.136.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.136.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.136.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.137.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.137.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.137.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.138.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.138.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.138.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.139.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.139.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.139.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.14.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.14.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.14.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.140.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.140.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.140.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.141.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.141.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.141.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.142.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.142.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.142.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.143.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.143.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.143.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.144.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.144.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.144.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.145.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.145.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.145.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.146.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.146.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.146.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.147.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.147.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.147.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.148.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.148.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.148.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.149.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.149.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.149.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.15.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.15.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.15.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.150.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.150.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.150.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.151.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.151.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.151.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.152.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.152.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.152.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.153.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.153.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.153.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.154.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.154.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.154.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.155.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.155.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.155.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.156.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.156.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.156.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.157.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.157.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.157.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.158.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.158.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.158.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.159.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.159.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.159.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.16.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.16.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.16.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.17.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.17.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.17.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.18.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.18.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.18.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.19.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.19.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.19.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.2.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.2.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.2.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.20.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.20.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.20.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.21.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.21.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.21.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.22.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.22.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.22.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.23.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.23.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.23.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.24.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.24.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.24.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.25.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.25.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.25.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.26.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.26.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.26.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.27.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.27.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.27.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.28.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.28.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.28.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.29.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.29.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.29.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.3.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.3.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.3.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.30.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.30.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.30.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.31.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.31.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.31.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.32.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.32.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.32.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.33.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.33.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.33.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.34.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.34.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.34.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.35.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.35.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.35.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.36.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.36.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.36.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.37.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.37.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.37.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.38.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.38.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.38.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.39.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.39.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.39.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.4.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.4.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.4.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.40.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.40.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.40.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.41.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.41.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.41.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.42.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.42.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.42.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.43.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.43.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.43.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.44.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.44.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.44.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.45.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.45.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.45.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.46.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.46.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.46.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.47.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.47.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.47.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.48.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.48.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.48.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.49.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.49.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.49.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.5.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.5.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.5.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.50.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.50.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.50.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.51.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.51.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.51.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.52.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.52.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.52.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.53.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.53.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.53.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.54.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.54.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.54.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.55.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.55.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.55.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.56.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.56.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.56.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.57.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.57.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.57.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.58.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.58.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.58.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.59.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.59.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.59.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.6.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.6.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.6.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.60.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.60.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.60.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.61.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.61.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.61.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.62.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.62.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.62.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.63.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.63.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.63.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.64.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.64.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.64.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.65.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.65.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.65.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.66.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.66.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.66.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.67.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.67.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.67.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.68.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.68.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.68.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.69.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.69.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.69.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.7.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.7.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.7.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.70.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.70.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.70.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.71.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.71.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.71.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.72.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.72.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.72.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.73.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.73.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.73.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.74.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.74.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.74.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.75.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.75.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.75.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.76.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.76.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.76.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.77.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.77.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.77.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.78.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.78.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.78.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.79.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.79.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.79.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.8.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.8.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.8.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.80.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.80.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.80.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.81.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.81.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.81.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.82.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.82.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.82.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.83.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.83.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.83.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.84.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.84.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.84.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.85.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.85.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.85.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.86.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.86.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.86.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.87.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.87.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.87.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.88.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.88.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.88.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.89.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.89.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.89.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.9.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.9.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.9.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.90.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.90.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.90.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.91.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.91.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.91.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.92.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.92.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.92.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.93.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.93.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.93.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.94.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.94.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.94.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.95.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.95.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.95.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.96.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.96.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.96.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.97.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.97.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.97.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.98.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.98.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.98.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.99.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.99.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.experts.99.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.gate.e_score_correction_bias": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.gate.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.k_norm.weight": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.k_proj.bias": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.q_norm.weight": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.q_proj.bias": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.v_proj.bias": "model-00066-of-00093.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00066-of-00093.safetensors", + "model.layers.66.input_layernorm.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.0.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.0.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.0.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.1.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.1.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.1.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.10.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.10.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.10.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.100.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.100.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.100.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.101.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.101.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.101.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.102.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.102.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.102.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.103.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.103.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.103.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.104.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.104.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.104.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.105.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.105.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.105.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.106.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.106.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.106.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.107.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.107.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.107.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.108.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.108.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.108.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.109.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.109.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.109.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.11.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.11.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.11.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.110.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.110.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.110.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.111.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.111.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.111.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.112.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.112.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.112.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.113.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.113.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.113.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.114.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.114.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.114.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.115.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.115.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.115.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.116.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.116.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.116.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.117.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.117.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.117.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.118.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.118.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.118.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.119.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.119.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.119.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.12.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.12.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.12.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.120.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.120.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.120.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.121.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.121.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.121.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.122.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.122.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.122.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.123.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.123.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.123.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.124.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.124.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.124.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.125.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.125.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.125.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.126.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.126.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.126.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.127.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.127.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.127.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.128.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.128.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.128.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.129.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.129.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.129.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.13.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.13.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.13.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.130.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.130.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.130.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.131.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.131.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.131.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.132.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.132.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.132.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.133.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.133.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.133.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.134.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.134.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.134.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.135.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.135.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.135.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.136.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.136.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.136.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.137.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.137.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.137.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.138.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.138.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.138.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.139.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.139.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.139.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.14.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.14.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.14.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.140.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.140.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.140.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.141.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.141.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.141.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.142.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.142.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.142.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.143.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.143.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.143.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.144.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.144.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.144.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.145.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.145.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.145.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.146.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.146.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.146.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.147.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.147.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.147.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.148.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.148.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.148.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.149.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.149.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.149.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.15.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.15.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.15.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.150.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.150.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.150.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.151.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.151.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.151.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.152.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.152.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.152.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.153.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.153.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.153.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.154.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.154.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.154.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.155.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.155.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.155.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.156.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.156.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.156.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.157.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.157.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.157.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.158.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.158.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.158.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.159.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.159.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.159.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.16.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.16.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.16.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.17.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.17.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.17.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.18.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.18.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.18.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.19.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.19.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.19.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.2.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.2.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.2.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.20.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.20.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.20.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.21.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.21.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.21.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.22.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.22.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.22.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.23.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.23.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.23.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.24.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.24.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.24.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.25.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.25.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.25.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.26.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.26.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.26.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.27.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.27.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.27.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.28.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.28.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.28.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.29.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.29.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.29.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.3.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.3.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.3.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.30.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.30.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.30.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.31.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.31.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.31.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.32.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.32.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.32.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.33.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.33.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.33.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.34.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.34.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.34.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.35.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.35.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.35.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.36.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.36.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.36.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.37.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.37.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.37.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.38.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.38.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.38.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.39.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.39.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.39.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.4.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.4.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.4.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.40.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.40.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.40.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.41.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.41.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.41.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.42.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.42.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.42.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.43.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.43.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.43.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.44.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.44.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.44.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.45.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.45.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.45.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.46.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.46.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.46.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.47.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.47.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.47.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.48.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.48.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.48.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.49.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.49.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.49.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.5.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.5.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.5.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.50.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.50.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.50.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.51.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.51.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.51.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.52.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.52.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.52.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.53.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.53.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.53.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.54.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.54.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.54.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.55.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.55.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.55.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.56.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.56.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.56.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.57.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.57.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.57.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.58.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.58.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.58.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.59.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.59.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.59.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.6.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.6.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.6.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.60.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.60.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.60.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.61.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.61.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.61.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.62.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.62.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.62.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.63.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.63.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.63.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.64.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.64.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.64.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.65.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.65.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.65.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.66.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.66.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.66.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.67.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.67.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.67.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.68.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.68.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.68.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.69.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.69.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.69.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.7.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.7.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.7.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.70.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.70.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.70.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.71.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.71.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.71.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.72.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.72.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.72.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.73.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.73.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.73.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.74.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.74.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.74.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.75.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.75.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.75.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.76.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.76.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.76.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.77.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.77.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.77.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.78.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.78.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.78.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.79.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.79.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.79.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.8.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.8.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.8.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.80.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.80.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.80.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.81.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.81.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.81.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.82.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.82.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.82.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.83.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.83.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.83.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.84.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.84.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.84.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.85.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.85.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.85.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.86.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.86.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.86.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.87.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.87.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.87.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.88.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.88.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.88.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.89.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.89.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.89.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.9.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.9.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.9.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.90.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.90.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.90.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.91.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.91.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.91.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.92.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.92.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.92.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.93.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.93.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.93.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.94.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.94.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.94.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.95.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.95.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.95.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.96.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.96.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.96.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.97.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.97.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.97.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.98.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.98.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.98.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.99.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.99.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.experts.99.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.gate.e_score_correction_bias": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.gate.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.k_norm.weight": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.k_proj.bias": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.q_norm.weight": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.q_proj.bias": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.v_proj.bias": "model-00067-of-00093.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00067-of-00093.safetensors", + "model.layers.67.input_layernorm.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.0.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.0.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.0.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.1.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.1.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.1.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.10.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.10.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.10.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.100.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.100.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.100.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.101.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.101.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.101.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.102.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.102.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.102.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.103.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.103.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.103.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.104.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.104.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.104.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.105.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.105.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.105.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.106.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.106.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.106.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.107.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.107.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.107.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.108.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.108.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.108.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.109.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.109.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.109.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.11.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.11.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.11.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.110.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.110.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.110.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.111.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.111.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.111.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.112.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.112.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.112.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.113.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.113.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.113.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.114.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.114.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.114.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.115.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.115.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.115.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.116.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.116.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.116.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.117.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.117.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.117.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.118.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.118.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.118.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.119.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.119.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.119.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.12.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.12.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.12.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.120.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.120.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.120.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.121.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.121.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.121.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.122.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.122.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.122.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.123.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.123.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.123.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.124.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.124.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.124.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.125.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.125.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.125.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.126.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.126.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.126.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.127.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.127.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.127.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.128.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.128.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.128.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.129.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.129.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.129.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.13.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.13.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.13.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.130.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.130.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.130.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.131.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.131.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.131.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.132.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.132.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.132.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.133.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.133.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.133.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.134.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.134.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.134.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.135.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.135.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.135.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.136.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.136.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.136.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.137.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.137.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.137.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.138.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.138.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.138.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.139.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.139.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.139.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.14.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.14.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.14.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.140.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.140.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.140.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.141.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.141.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.141.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.142.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.142.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.142.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.143.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.143.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.143.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.144.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.144.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.144.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.145.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.145.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.145.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.146.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.146.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.146.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.147.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.147.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.147.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.148.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.148.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.148.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.149.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.149.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.149.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.15.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.15.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.15.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.150.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.150.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.150.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.151.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.151.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.151.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.152.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.152.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.152.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.153.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.153.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.153.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.154.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.154.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.154.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.155.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.155.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.155.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.156.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.156.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.156.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.157.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.157.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.157.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.158.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.158.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.158.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.159.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.159.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.159.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.16.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.16.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.16.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.17.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.17.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.17.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.18.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.18.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.18.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.19.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.19.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.19.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.2.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.2.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.2.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.20.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.20.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.20.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.21.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.21.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.21.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.22.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.22.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.22.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.23.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.23.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.23.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.24.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.24.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.24.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.25.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.25.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.25.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.26.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.26.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.26.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.27.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.27.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.27.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.28.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.28.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.28.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.29.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.29.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.29.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.3.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.3.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.3.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.30.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.30.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.30.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.31.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.31.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.31.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.32.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.32.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.32.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.33.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.33.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.33.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.34.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.34.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.34.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.35.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.35.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.35.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.36.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.36.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.36.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.37.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.37.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.37.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.38.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.38.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.38.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.39.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.39.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.39.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.4.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.4.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.4.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.40.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.40.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.40.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.41.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.41.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.41.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.42.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.42.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.42.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.43.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.43.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.43.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.44.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.44.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.44.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.45.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.45.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.45.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.46.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.46.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.46.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.47.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.47.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.47.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.48.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.48.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.48.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.49.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.49.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.49.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.5.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.5.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.5.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.50.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.50.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.50.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.51.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.51.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.51.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.52.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.52.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.52.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.53.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.53.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.53.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.54.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.54.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.54.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.55.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.55.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.55.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.56.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.56.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.56.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.57.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.57.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.57.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.58.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.58.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.58.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.59.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.59.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.59.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.6.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.6.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.6.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.60.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.60.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.60.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.61.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.61.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.61.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.62.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.62.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.62.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.63.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.63.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.63.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.64.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.64.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.64.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.65.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.65.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.65.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.66.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.66.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.66.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.67.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.67.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.67.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.68.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.68.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.68.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.69.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.69.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.69.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.7.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.7.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.7.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.70.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.70.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.70.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.71.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.71.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.71.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.72.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.72.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.72.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.73.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.73.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.73.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.74.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.74.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.74.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.75.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.75.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.75.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.76.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.76.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.76.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.77.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.77.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.77.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.78.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.78.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.78.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.79.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.79.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.79.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.8.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.8.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.8.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.80.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.80.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.80.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.81.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.81.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.81.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.82.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.82.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.82.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.83.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.83.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.83.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.84.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.84.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.84.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.85.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.85.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.85.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.86.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.86.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.86.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.87.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.87.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.87.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.88.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.88.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.88.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.89.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.89.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.89.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.9.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.9.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.9.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.90.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.90.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.90.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.91.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.91.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.91.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.92.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.92.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.92.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.93.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.93.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.93.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.94.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.94.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.94.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.95.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.95.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.95.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.96.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.96.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.96.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.97.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.97.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.97.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.98.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.98.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.98.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.99.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.99.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.experts.99.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.gate.e_score_correction_bias": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.gate.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.k_norm.weight": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.k_proj.bias": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.q_norm.weight": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.q_proj.bias": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.v_proj.bias": "model-00068-of-00093.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00068-of-00093.safetensors", + "model.layers.68.input_layernorm.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.0.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.0.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.0.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.1.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.1.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.1.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.10.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.10.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.10.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.100.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.100.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.100.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.101.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.101.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.101.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.102.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.102.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.102.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.103.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.103.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.103.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.104.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.104.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.104.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.105.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.105.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.105.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.106.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.106.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.106.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.107.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.107.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.107.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.108.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.108.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.108.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.109.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.109.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.109.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.11.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.11.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.11.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.110.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.110.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.110.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.111.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.111.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.111.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.112.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.112.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.112.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.113.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.113.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.113.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.114.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.114.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.114.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.115.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.115.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.115.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.116.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.116.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.116.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.117.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.117.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.117.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.118.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.118.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.118.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.119.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.119.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.119.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.12.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.12.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.12.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.120.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.120.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.120.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.121.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.121.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.121.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.122.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.122.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.122.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.123.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.123.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.123.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.124.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.124.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.124.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.125.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.125.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.125.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.126.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.126.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.126.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.127.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.127.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.127.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.128.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.128.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.128.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.129.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.129.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.129.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.13.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.13.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.13.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.130.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.130.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.130.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.131.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.131.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.131.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.132.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.132.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.132.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.133.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.133.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.133.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.134.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.134.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.134.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.135.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.135.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.135.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.136.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.136.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.136.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.137.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.137.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.137.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.138.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.138.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.138.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.139.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.139.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.139.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.14.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.14.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.14.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.140.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.140.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.140.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.141.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.141.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.141.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.142.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.142.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.142.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.143.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.143.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.143.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.144.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.144.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.144.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.145.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.145.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.145.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.146.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.146.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.146.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.147.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.147.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.147.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.148.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.148.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.148.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.149.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.149.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.149.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.15.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.15.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.15.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.150.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.150.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.150.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.151.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.151.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.151.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.152.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.152.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.152.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.153.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.153.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.153.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.154.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.154.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.154.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.155.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.155.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.155.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.156.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.156.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.156.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.157.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.157.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.157.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.158.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.158.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.158.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.159.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.159.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.159.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.16.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.16.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.16.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.17.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.17.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.17.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.18.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.18.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.18.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.19.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.19.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.19.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.2.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.2.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.2.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.20.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.20.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.20.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.21.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.21.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.21.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.22.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.22.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.22.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.23.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.23.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.23.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.24.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.24.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.24.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.25.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.25.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.25.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.26.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.26.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.26.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.27.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.27.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.27.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.28.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.28.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.28.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.29.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.29.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.29.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.3.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.3.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.3.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.30.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.30.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.30.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.31.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.31.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.31.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.32.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.32.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.32.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.33.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.33.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.33.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.34.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.34.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.34.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.35.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.35.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.35.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.36.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.36.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.36.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.37.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.37.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.37.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.38.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.38.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.38.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.39.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.39.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.39.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.4.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.4.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.4.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.40.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.40.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.40.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.41.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.41.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.41.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.42.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.42.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.42.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.43.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.43.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.43.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.44.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.44.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.44.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.45.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.45.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.45.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.46.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.46.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.46.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.47.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.47.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.47.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.48.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.48.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.48.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.49.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.49.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.49.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.5.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.5.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.5.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.50.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.50.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.50.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.51.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.51.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.51.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.52.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.52.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.52.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.53.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.53.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.53.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.54.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.54.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.54.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.55.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.55.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.55.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.56.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.56.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.56.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.57.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.57.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.57.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.58.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.58.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.58.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.59.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.59.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.59.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.6.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.6.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.6.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.60.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.60.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.60.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.61.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.61.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.61.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.62.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.62.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.62.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.63.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.63.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.63.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.64.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.64.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.64.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.65.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.65.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.65.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.66.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.66.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.66.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.67.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.67.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.67.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.68.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.68.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.68.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.69.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.69.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.69.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.7.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.7.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.7.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.70.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.70.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.70.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.71.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.71.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.71.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.72.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.72.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.72.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.73.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.73.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.73.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.74.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.74.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.74.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.75.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.75.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.75.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.76.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.76.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.76.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.77.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.77.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.77.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.78.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.78.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.78.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.79.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.79.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.79.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.8.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.8.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.8.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.80.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.80.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.80.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.81.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.81.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.81.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.82.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.82.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.82.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.83.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.83.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.83.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.84.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.84.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.84.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.85.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.85.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.85.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.86.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.86.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.86.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.87.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.87.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.87.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.88.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.88.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.88.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.89.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.89.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.89.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.9.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.9.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.9.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.90.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.90.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.90.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.91.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.91.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.91.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.92.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.92.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.92.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.93.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.93.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.93.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.94.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.94.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.94.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.95.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.95.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.95.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.96.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.96.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.96.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.97.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.97.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.97.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.98.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.98.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.98.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.99.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.99.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.experts.99.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.gate.e_score_correction_bias": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.gate.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.k_norm.weight": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.k_proj.bias": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.q_norm.weight": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.q_proj.bias": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.v_proj.bias": "model-00069-of-00093.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00069-of-00093.safetensors", + "model.layers.69.input_layernorm.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.0.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.0.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.0.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.1.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.1.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.1.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.10.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.10.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.10.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.100.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.100.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.100.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.101.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.101.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.101.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.102.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.102.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.102.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.103.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.103.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.103.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.104.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.104.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.104.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.105.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.105.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.105.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.106.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.106.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.106.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.107.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.107.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.107.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.108.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.108.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.108.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.109.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.109.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.109.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.11.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.11.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.11.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.110.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.110.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.110.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.111.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.111.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.111.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.112.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.112.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.112.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.113.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.113.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.113.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.114.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.114.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.114.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.115.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.115.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.115.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.116.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.116.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.116.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.117.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.117.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.117.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.118.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.118.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.118.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.119.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.119.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.119.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.12.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.12.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.12.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.120.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.120.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.120.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.121.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.121.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.121.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.122.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.122.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.122.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.123.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.123.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.123.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.124.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.124.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.124.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.125.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.125.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.125.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.126.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.126.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.126.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.127.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.127.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.127.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.128.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.128.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.128.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.129.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.129.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.129.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.13.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.13.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.13.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.130.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.130.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.130.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.131.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.131.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.131.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.132.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.132.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.132.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.133.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.133.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.133.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.134.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.134.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.134.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.135.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.135.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.135.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.136.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.136.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.136.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.137.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.137.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.137.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.138.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.138.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.138.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.139.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.139.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.139.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.14.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.14.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.14.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.140.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.140.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.140.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.141.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.141.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.141.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.142.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.142.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.142.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.143.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.143.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.143.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.144.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.144.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.144.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.145.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.145.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.145.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.146.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.146.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.146.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.147.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.147.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.147.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.148.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.148.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.148.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.149.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.149.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.149.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.15.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.15.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.15.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.150.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.150.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.150.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.151.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.151.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.151.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.152.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.152.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.152.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.153.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.153.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.153.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.154.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.154.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.154.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.155.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.155.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.155.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.156.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.156.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.156.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.157.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.157.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.157.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.158.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.158.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.158.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.159.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.159.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.159.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.16.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.16.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.16.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.17.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.17.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.17.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.18.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.18.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.18.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.19.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.19.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.19.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.2.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.2.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.2.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.20.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.20.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.20.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.21.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.21.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.21.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.22.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.22.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.22.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.23.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.23.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.23.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.24.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.24.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.24.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.25.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.25.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.25.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.26.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.26.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.26.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.27.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.27.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.27.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.28.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.28.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.28.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.29.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.29.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.29.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.3.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.3.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.3.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.30.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.30.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.30.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.31.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.31.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.31.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.32.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.32.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.32.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.33.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.33.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.33.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.34.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.34.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.34.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.35.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.35.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.35.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.36.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.36.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.36.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.37.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.37.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.37.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.38.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.38.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.38.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.39.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.39.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.39.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.4.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.4.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.4.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.40.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.40.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.40.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.41.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.41.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.41.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.42.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.42.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.42.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.43.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.43.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.43.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.44.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.44.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.44.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.45.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.45.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.45.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.46.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.46.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.46.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.47.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.47.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.47.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.48.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.48.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.48.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.49.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.49.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.49.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.5.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.5.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.5.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.50.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.50.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.50.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.51.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.51.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.51.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.52.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.52.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.52.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.53.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.53.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.53.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.54.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.54.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.54.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.55.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.55.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.55.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.56.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.56.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.56.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.57.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.57.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.57.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.58.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.58.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.58.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.59.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.59.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.59.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.6.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.6.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.6.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.60.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.60.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.60.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.61.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.61.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.61.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.62.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.62.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.62.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.63.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.63.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.63.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.64.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.64.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.64.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.65.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.65.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.65.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.66.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.66.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.66.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.67.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.67.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.67.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.68.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.68.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.68.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.69.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.69.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.69.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.7.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.7.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.7.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.70.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.70.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.70.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.71.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.71.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.71.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.72.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.72.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.72.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.73.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.73.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.73.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.74.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.74.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.74.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.75.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.75.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.75.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.76.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.76.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.76.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.77.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.77.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.77.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.78.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.78.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.78.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.79.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.79.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.79.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.8.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.8.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.8.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.80.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.80.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.80.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.81.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.81.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.81.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.82.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.82.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.82.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.83.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.83.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.83.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.84.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.84.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.84.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.85.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.85.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.85.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.86.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.86.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.86.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.87.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.87.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.87.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.88.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.88.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.88.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.89.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.89.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.89.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.9.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.9.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.9.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.90.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.90.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.90.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.91.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.91.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.91.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.92.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.92.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.92.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.93.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.93.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.93.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.94.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.94.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.94.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.95.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.95.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.95.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.96.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.96.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.96.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.97.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.97.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.97.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.98.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.98.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.98.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.99.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.99.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.experts.99.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.gate.e_score_correction_bias": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.gate.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.k_norm.weight": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.k_proj.bias": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.q_norm.weight": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.q_proj.bias": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.v_proj.bias": "model-00070-of-00093.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00070-of-00093.safetensors", + "model.layers.70.input_layernorm.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.0.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.0.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.0.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.1.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.1.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.1.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.10.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.10.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.10.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.100.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.100.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.100.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.101.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.101.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.101.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.102.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.102.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.102.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.103.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.103.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.103.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.104.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.104.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.104.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.105.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.105.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.105.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.106.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.106.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.106.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.107.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.107.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.107.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.108.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.108.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.108.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.109.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.109.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.109.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.11.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.11.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.11.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.110.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.110.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.110.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.111.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.111.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.111.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.112.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.112.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.112.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.113.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.113.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.113.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.114.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.114.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.114.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.115.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.115.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.115.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.116.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.116.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.116.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.117.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.117.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.117.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.118.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.118.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.118.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.119.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.119.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.119.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.12.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.12.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.12.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.120.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.120.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.120.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.121.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.121.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.121.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.122.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.122.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.122.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.123.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.123.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.123.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.124.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.124.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.124.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.125.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.125.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.125.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.126.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.126.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.126.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.127.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.127.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.127.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.128.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.128.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.128.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.129.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.129.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.129.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.13.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.13.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.13.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.130.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.130.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.130.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.131.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.131.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.131.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.132.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.132.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.132.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.133.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.133.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.133.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.134.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.134.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.134.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.135.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.135.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.135.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.136.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.136.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.136.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.137.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.137.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.137.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.138.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.138.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.138.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.139.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.139.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.139.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.14.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.14.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.14.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.140.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.140.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.140.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.141.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.141.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.141.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.142.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.142.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.142.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.143.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.143.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.143.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.144.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.144.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.144.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.145.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.145.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.145.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.146.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.146.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.146.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.147.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.147.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.147.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.148.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.148.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.148.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.149.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.149.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.149.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.15.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.15.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.15.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.150.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.150.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.150.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.151.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.151.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.151.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.152.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.152.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.152.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.153.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.153.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.153.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.154.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.154.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.154.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.155.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.155.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.155.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.156.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.156.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.156.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.157.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.157.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.157.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.158.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.158.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.158.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.159.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.159.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.159.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.16.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.16.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.16.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.17.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.17.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.17.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.18.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.18.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.18.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.19.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.19.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.19.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.2.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.2.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.2.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.20.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.20.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.20.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.21.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.21.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.21.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.22.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.22.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.22.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.23.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.23.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.23.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.24.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.24.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.24.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.25.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.25.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.25.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.26.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.26.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.26.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.27.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.27.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.27.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.28.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.28.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.28.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.29.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.29.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.29.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.3.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.3.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.3.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.30.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.30.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.30.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.31.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.31.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.31.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.32.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.32.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.32.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.33.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.33.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.33.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.34.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.34.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.34.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.35.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.35.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.35.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.36.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.36.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.36.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.37.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.37.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.37.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.38.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.38.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.38.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.39.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.39.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.39.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.4.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.4.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.4.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.40.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.40.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.40.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.41.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.41.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.41.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.42.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.42.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.42.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.43.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.43.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.43.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.44.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.44.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.44.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.45.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.45.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.45.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.46.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.46.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.46.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.47.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.47.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.47.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.48.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.48.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.48.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.49.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.49.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.49.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.5.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.5.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.5.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.50.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.50.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.50.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.51.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.51.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.51.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.52.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.52.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.52.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.53.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.53.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.53.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.54.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.54.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.54.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.55.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.55.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.55.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.56.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.56.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.56.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.57.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.57.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.57.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.58.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.58.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.58.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.59.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.59.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.59.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.6.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.6.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.6.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.60.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.60.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.60.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.61.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.61.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.61.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.62.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.62.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.62.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.63.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.63.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.63.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.64.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.64.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.64.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.65.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.65.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.65.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.66.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.66.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.66.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.67.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.67.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.67.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.68.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.68.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.68.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.69.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.69.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.69.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.7.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.7.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.7.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.70.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.70.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.70.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.71.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.71.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.71.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.72.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.72.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.72.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.73.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.73.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.73.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.74.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.74.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.74.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.75.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.75.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.75.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.76.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.76.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.76.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.77.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.77.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.77.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.78.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.78.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.78.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.79.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.79.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.79.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.8.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.8.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.8.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.80.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.80.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.80.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.81.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.81.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.81.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.82.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.82.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.82.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.83.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.83.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.83.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.84.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.84.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.84.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.85.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.85.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.85.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.86.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.86.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.86.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.87.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.87.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.87.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.88.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.88.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.88.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.89.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.89.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.89.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.9.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.9.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.9.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.90.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.90.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.90.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.91.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.91.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.91.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.92.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.92.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.92.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.93.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.93.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.93.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.94.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.94.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.94.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.95.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.95.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.95.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.96.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.96.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.96.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.97.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.97.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.97.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.98.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.98.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.98.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.99.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.99.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.experts.99.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.gate.e_score_correction_bias": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.gate.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.k_norm.weight": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.k_proj.bias": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.q_norm.weight": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.q_proj.bias": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.v_proj.bias": "model-00071-of-00093.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00071-of-00093.safetensors", + "model.layers.71.input_layernorm.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.0.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.0.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.0.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.1.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.1.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.1.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.10.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.10.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.10.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.100.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.100.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.100.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.101.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.101.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.101.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.102.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.102.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.102.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.103.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.103.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.103.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.104.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.104.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.104.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.105.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.105.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.105.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.106.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.106.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.106.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.107.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.107.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.107.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.108.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.108.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.108.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.109.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.109.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.109.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.11.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.11.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.11.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.110.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.110.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.110.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.111.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.111.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.111.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.112.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.112.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.112.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.113.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.113.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.113.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.114.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.114.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.114.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.115.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.115.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.115.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.116.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.116.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.116.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.117.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.117.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.117.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.118.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.118.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.118.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.119.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.119.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.119.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.12.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.12.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.12.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.120.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.120.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.120.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.121.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.121.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.121.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.122.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.122.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.122.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.123.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.123.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.123.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.124.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.124.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.124.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.125.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.125.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.125.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.126.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.126.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.126.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.127.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.127.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.127.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.128.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.128.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.128.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.129.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.129.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.129.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.13.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.13.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.13.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.130.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.130.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.130.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.131.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.131.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.131.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.132.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.132.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.132.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.133.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.133.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.133.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.134.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.134.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.134.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.135.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.135.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.135.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.136.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.136.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.136.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.137.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.137.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.137.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.138.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.138.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.138.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.139.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.139.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.139.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.14.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.14.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.14.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.140.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.140.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.140.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.141.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.141.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.141.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.142.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.142.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.142.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.143.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.143.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.143.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.144.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.144.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.144.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.145.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.145.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.145.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.146.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.146.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.146.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.147.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.147.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.147.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.148.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.148.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.148.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.149.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.149.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.149.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.15.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.15.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.15.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.150.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.150.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.150.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.151.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.151.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.151.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.152.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.152.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.152.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.153.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.153.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.153.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.154.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.154.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.154.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.155.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.155.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.155.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.156.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.156.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.156.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.157.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.157.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.157.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.158.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.158.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.158.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.159.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.159.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.159.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.16.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.16.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.16.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.17.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.17.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.17.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.18.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.18.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.18.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.19.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.19.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.19.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.2.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.2.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.2.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.20.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.20.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.20.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.21.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.21.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.21.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.22.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.22.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.22.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.23.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.23.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.23.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.24.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.24.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.24.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.25.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.25.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.25.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.26.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.26.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.26.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.27.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.27.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.27.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.28.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.28.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.28.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.29.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.29.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.29.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.3.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.3.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.3.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.30.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.30.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.30.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.31.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.31.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.31.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.32.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.32.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.32.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.33.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.33.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.33.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.34.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.34.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.34.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.35.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.35.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.35.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.36.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.36.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.36.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.37.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.37.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.37.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.38.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.38.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.38.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.39.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.39.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.39.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.4.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.4.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.4.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.40.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.40.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.40.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.41.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.41.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.41.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.42.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.42.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.42.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.43.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.43.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.43.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.44.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.44.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.44.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.45.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.45.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.45.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.46.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.46.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.46.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.47.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.47.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.47.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.48.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.48.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.48.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.49.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.49.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.49.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.5.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.5.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.5.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.50.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.50.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.50.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.51.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.51.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.51.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.52.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.52.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.52.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.53.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.53.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.53.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.54.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.54.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.54.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.55.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.55.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.55.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.56.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.56.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.56.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.57.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.57.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.57.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.58.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.58.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.58.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.59.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.59.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.59.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.6.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.6.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.6.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.60.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.60.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.60.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.61.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.61.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.61.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.62.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.62.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.62.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.63.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.63.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.63.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.64.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.64.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.64.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.65.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.65.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.65.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.66.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.66.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.66.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.67.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.67.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.67.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.68.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.68.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.68.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.69.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.69.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.69.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.7.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.7.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.7.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.70.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.70.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.70.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.71.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.71.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.71.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.72.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.72.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.72.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.73.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.73.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.73.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.74.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.74.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.74.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.75.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.75.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.75.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.76.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.76.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.76.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.77.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.77.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.77.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.78.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.78.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.78.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.79.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.79.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.79.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.8.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.8.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.8.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.80.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.80.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.80.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.81.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.81.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.81.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.82.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.82.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.82.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.83.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.83.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.83.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.84.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.84.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.84.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.85.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.85.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.85.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.86.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.86.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.86.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.87.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.87.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.87.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.88.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.88.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.88.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.89.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.89.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.89.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.9.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.9.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.9.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.90.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.90.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.90.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.91.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.91.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.91.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.92.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.92.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.92.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.93.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.93.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.93.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.94.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.94.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.94.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.95.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.95.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.95.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.96.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.96.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.96.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.97.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.97.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.97.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.98.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.98.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.98.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.99.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.99.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.experts.99.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.gate.e_score_correction_bias": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.gate.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.k_norm.weight": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.k_proj.bias": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.q_norm.weight": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.q_proj.bias": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.v_proj.bias": "model-00072-of-00093.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00072-of-00093.safetensors", + "model.layers.72.input_layernorm.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.0.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.0.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.0.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.1.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.1.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.1.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.10.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.10.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.10.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.100.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.100.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.100.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.101.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.101.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.101.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.102.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.102.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.102.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.103.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.103.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.103.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.104.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.104.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.104.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.105.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.105.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.105.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.106.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.106.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.106.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.107.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.107.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.107.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.108.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.108.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.108.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.109.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.109.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.109.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.11.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.11.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.11.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.110.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.110.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.110.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.111.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.111.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.111.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.112.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.112.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.112.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.113.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.113.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.113.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.114.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.114.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.114.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.115.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.115.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.115.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.116.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.116.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.116.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.117.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.117.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.117.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.118.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.118.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.118.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.119.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.119.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.119.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.12.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.12.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.12.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.120.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.120.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.120.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.121.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.121.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.121.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.122.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.122.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.122.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.123.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.123.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.123.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.124.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.124.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.124.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.125.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.125.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.125.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.126.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.126.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.126.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.127.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.127.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.127.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.128.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.128.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.128.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.129.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.129.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.129.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.13.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.13.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.13.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.130.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.130.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.130.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.131.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.131.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.131.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.132.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.132.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.132.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.133.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.133.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.133.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.134.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.134.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.134.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.135.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.135.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.135.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.136.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.136.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.136.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.137.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.137.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.137.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.138.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.138.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.138.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.139.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.139.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.139.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.14.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.14.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.14.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.140.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.140.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.140.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.141.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.141.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.141.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.142.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.142.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.142.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.143.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.143.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.143.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.144.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.144.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.144.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.145.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.145.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.145.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.146.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.146.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.146.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.147.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.147.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.147.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.148.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.148.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.148.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.149.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.149.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.149.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.15.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.15.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.15.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.150.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.150.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.150.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.151.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.151.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.151.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.152.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.152.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.152.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.153.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.153.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.153.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.154.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.154.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.154.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.155.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.155.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.155.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.156.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.156.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.156.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.157.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.157.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.157.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.158.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.158.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.158.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.159.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.159.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.159.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.16.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.16.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.16.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.17.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.17.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.17.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.18.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.18.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.18.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.19.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.19.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.19.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.2.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.2.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.2.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.20.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.20.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.20.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.21.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.21.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.21.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.22.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.22.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.22.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.23.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.23.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.23.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.24.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.24.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.24.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.25.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.25.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.25.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.26.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.26.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.26.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.27.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.27.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.27.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.28.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.28.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.28.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.29.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.29.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.29.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.3.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.3.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.3.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.30.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.30.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.30.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.31.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.31.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.31.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.32.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.32.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.32.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.33.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.33.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.33.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.34.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.34.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.34.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.35.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.35.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.35.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.36.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.36.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.36.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.37.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.37.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.37.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.38.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.38.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.38.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.39.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.39.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.39.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.4.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.4.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.4.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.40.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.40.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.40.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.41.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.41.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.41.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.42.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.42.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.42.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.43.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.43.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.43.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.44.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.44.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.44.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.45.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.45.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.45.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.46.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.46.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.46.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.47.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.47.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.47.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.48.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.48.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.48.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.49.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.49.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.49.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.5.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.5.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.5.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.50.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.50.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.50.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.51.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.51.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.51.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.52.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.52.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.52.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.53.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.53.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.53.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.54.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.54.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.54.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.55.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.55.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.55.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.56.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.56.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.56.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.57.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.57.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.57.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.58.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.58.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.58.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.59.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.59.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.59.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.6.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.6.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.6.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.60.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.60.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.60.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.61.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.61.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.61.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.62.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.62.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.62.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.63.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.63.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.63.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.64.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.64.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.64.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.65.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.65.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.65.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.66.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.66.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.66.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.67.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.67.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.67.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.68.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.68.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.68.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.69.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.69.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.69.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.7.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.7.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.7.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.70.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.70.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.70.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.71.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.71.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.71.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.72.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.72.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.72.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.73.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.73.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.73.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.74.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.74.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.74.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.75.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.75.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.75.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.76.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.76.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.76.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.77.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.77.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.77.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.78.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.78.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.78.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.79.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.79.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.79.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.8.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.8.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.8.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.80.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.80.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.80.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.81.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.81.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.81.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.82.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.82.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.82.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.83.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.83.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.83.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.84.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.84.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.84.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.85.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.85.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.85.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.86.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.86.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.86.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.87.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.87.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.87.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.88.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.88.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.88.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.89.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.89.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.89.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.9.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.9.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.9.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.90.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.90.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.90.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.91.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.91.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.91.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.92.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.92.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.92.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.93.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.93.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.93.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.94.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.94.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.94.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.95.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.95.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.95.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.96.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.96.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.96.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.97.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.97.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.97.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.98.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.98.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.98.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.99.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.99.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.experts.99.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.gate.e_score_correction_bias": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.gate.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.k_norm.weight": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.k_proj.bias": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.q_norm.weight": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.q_proj.bias": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.v_proj.bias": "model-00073-of-00093.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00073-of-00093.safetensors", + "model.layers.73.input_layernorm.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.0.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.0.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.0.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.1.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.1.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.1.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.10.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.10.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.10.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.100.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.100.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.100.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.101.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.101.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.101.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.102.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.102.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.102.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.103.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.103.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.103.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.104.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.104.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.104.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.105.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.105.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.105.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.106.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.106.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.106.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.107.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.107.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.107.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.108.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.108.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.108.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.109.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.109.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.109.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.11.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.11.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.11.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.110.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.110.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.110.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.111.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.111.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.111.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.112.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.112.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.112.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.113.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.113.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.113.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.114.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.114.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.114.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.115.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.115.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.115.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.116.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.116.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.116.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.117.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.117.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.117.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.118.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.118.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.118.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.119.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.119.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.119.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.12.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.12.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.12.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.120.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.120.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.120.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.121.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.121.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.121.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.122.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.122.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.122.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.123.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.123.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.123.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.124.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.124.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.124.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.125.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.125.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.125.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.126.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.126.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.126.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.127.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.127.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.127.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.128.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.128.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.128.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.129.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.129.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.129.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.13.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.13.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.13.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.130.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.130.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.130.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.131.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.131.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.131.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.132.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.132.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.132.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.133.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.133.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.133.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.134.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.134.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.134.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.135.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.135.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.135.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.136.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.136.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.136.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.137.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.137.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.137.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.138.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.138.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.138.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.139.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.139.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.139.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.14.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.14.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.14.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.140.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.140.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.140.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.141.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.141.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.141.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.142.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.142.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.142.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.143.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.143.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.143.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.144.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.144.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.144.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.145.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.145.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.145.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.146.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.146.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.146.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.147.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.147.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.147.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.148.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.148.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.148.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.149.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.149.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.149.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.15.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.15.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.15.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.150.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.150.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.150.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.151.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.151.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.151.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.152.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.152.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.152.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.153.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.153.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.153.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.154.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.154.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.154.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.155.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.155.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.155.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.156.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.156.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.156.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.157.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.157.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.157.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.158.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.158.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.158.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.159.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.159.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.159.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.16.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.16.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.16.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.17.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.17.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.17.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.18.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.18.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.18.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.19.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.19.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.19.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.2.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.2.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.2.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.20.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.20.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.20.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.21.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.21.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.21.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.22.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.22.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.22.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.23.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.23.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.23.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.24.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.24.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.24.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.25.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.25.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.25.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.26.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.26.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.26.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.27.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.27.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.27.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.28.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.28.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.28.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.29.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.29.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.29.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.3.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.3.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.3.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.30.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.30.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.30.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.31.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.31.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.31.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.32.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.32.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.32.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.33.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.33.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.33.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.34.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.34.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.34.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.35.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.35.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.35.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.36.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.36.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.36.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.37.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.37.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.37.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.38.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.38.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.38.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.39.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.39.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.39.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.4.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.4.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.4.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.40.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.40.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.40.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.41.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.41.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.41.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.42.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.42.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.42.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.43.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.43.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.43.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.44.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.44.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.44.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.45.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.45.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.45.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.46.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.46.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.46.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.47.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.47.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.47.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.48.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.48.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.48.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.49.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.49.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.49.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.5.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.5.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.5.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.50.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.50.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.50.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.51.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.51.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.51.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.52.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.52.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.52.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.53.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.53.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.53.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.54.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.54.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.54.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.55.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.55.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.55.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.56.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.56.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.56.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.57.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.57.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.57.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.58.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.58.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.58.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.59.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.59.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.59.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.6.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.6.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.6.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.60.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.60.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.60.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.61.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.61.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.61.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.62.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.62.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.62.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.63.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.63.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.63.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.64.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.64.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.64.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.65.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.65.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.65.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.66.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.66.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.66.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.67.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.67.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.67.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.68.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.68.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.68.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.69.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.69.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.69.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.7.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.7.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.7.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.70.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.70.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.70.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.71.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.71.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.71.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.72.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.72.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.72.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.73.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.73.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.73.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.74.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.74.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.74.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.75.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.75.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.75.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.76.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.76.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.76.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.77.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.77.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.77.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.78.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.78.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.78.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.79.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.79.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.79.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.8.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.8.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.8.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.80.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.80.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.80.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.81.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.81.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.81.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.82.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.82.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.82.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.83.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.83.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.83.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.84.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.84.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.84.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.85.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.85.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.85.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.86.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.86.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.86.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.87.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.87.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.87.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.88.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.88.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.88.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.89.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.89.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.89.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.9.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.9.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.9.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.90.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.90.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.90.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.91.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.91.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.91.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.92.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.92.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.92.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.93.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.93.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.93.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.94.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.94.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.94.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.95.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.95.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.95.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.96.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.96.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.96.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.97.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.97.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.97.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.98.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.98.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.98.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.99.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.99.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.experts.99.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.gate.e_score_correction_bias": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.gate.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.k_norm.weight": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.k_proj.bias": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.q_norm.weight": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.q_proj.bias": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.v_proj.bias": "model-00074-of-00093.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00074-of-00093.safetensors", + "model.layers.74.input_layernorm.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.0.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.0.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.0.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.1.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.1.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.1.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.10.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.10.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.10.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.100.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.100.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.100.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.101.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.101.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.101.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.102.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.102.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.102.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.103.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.103.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.103.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.104.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.104.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.104.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.105.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.105.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.105.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.106.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.106.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.106.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.107.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.107.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.107.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.108.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.108.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.108.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.109.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.109.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.109.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.11.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.11.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.11.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.110.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.110.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.110.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.111.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.111.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.111.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.112.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.112.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.112.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.113.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.113.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.113.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.114.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.114.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.114.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.115.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.115.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.115.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.116.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.116.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.116.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.117.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.117.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.117.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.118.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.118.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.118.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.119.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.119.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.119.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.12.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.12.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.12.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.120.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.120.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.120.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.121.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.121.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.121.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.122.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.122.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.122.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.123.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.123.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.123.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.124.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.124.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.124.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.125.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.125.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.125.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.126.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.126.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.126.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.127.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.127.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.127.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.128.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.128.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.128.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.129.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.129.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.129.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.13.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.13.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.13.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.130.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.130.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.130.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.131.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.131.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.131.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.132.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.132.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.132.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.133.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.133.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.133.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.134.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.134.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.134.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.135.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.135.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.135.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.136.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.136.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.136.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.137.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.137.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.137.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.138.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.138.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.138.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.139.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.139.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.139.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.14.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.14.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.14.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.140.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.140.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.140.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.141.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.141.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.141.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.142.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.142.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.142.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.143.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.143.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.143.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.144.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.144.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.144.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.145.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.145.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.145.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.146.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.146.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.146.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.147.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.147.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.147.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.148.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.148.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.148.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.149.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.149.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.149.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.15.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.15.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.15.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.150.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.150.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.150.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.151.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.151.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.151.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.152.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.152.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.152.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.153.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.153.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.153.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.154.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.154.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.154.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.155.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.155.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.155.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.156.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.156.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.156.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.157.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.157.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.157.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.158.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.158.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.158.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.159.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.159.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.159.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.16.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.16.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.16.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.17.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.17.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.17.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.18.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.18.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.18.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.19.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.19.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.19.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.2.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.2.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.2.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.20.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.20.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.20.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.21.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.21.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.21.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.22.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.22.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.22.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.23.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.23.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.23.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.24.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.24.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.24.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.25.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.25.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.25.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.26.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.26.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.26.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.27.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.27.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.27.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.28.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.28.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.28.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.29.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.29.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.29.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.3.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.3.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.3.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.30.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.30.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.30.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.31.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.31.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.31.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.32.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.32.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.32.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.33.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.33.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.33.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.34.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.34.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.34.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.35.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.35.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.35.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.36.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.36.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.36.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.37.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.37.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.37.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.38.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.38.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.38.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.39.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.39.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.39.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.4.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.4.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.4.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.40.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.40.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.40.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.41.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.41.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.41.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.42.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.42.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.42.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.43.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.43.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.43.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.44.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.44.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.44.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.45.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.45.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.45.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.46.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.46.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.46.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.47.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.47.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.47.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.48.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.48.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.48.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.49.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.49.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.49.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.5.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.5.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.5.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.50.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.50.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.50.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.51.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.51.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.51.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.52.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.52.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.52.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.53.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.53.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.53.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.54.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.54.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.54.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.55.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.55.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.55.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.56.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.56.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.56.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.57.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.57.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.57.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.58.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.58.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.58.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.59.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.59.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.59.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.6.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.6.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.6.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.60.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.60.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.60.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.61.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.61.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.61.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.62.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.62.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.62.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.63.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.63.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.63.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.64.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.64.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.64.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.65.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.65.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.65.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.66.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.66.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.66.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.67.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.67.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.67.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.68.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.68.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.68.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.69.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.69.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.69.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.7.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.7.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.7.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.70.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.70.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.70.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.71.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.71.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.71.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.72.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.72.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.72.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.73.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.73.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.73.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.74.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.74.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.74.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.75.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.75.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.75.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.76.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.76.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.76.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.77.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.77.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.77.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.78.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.78.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.78.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.79.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.79.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.79.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.8.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.8.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.8.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.80.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.80.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.80.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.81.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.81.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.81.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.82.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.82.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.82.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.83.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.83.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.83.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.84.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.84.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.84.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.85.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.85.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.85.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.86.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.86.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.86.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.87.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.87.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.87.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.88.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.88.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.88.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.89.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.89.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.89.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.9.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.9.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.9.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.90.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.90.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.90.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.91.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.91.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.91.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.92.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.92.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.92.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.93.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.93.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.93.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.94.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.94.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.94.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.95.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.95.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.95.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.96.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.96.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.96.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.97.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.97.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.97.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.98.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.98.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.98.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.99.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.99.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.experts.99.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.gate.e_score_correction_bias": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.gate.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.k_norm.weight": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.k_proj.bias": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.q_norm.weight": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.q_proj.bias": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.v_proj.bias": "model-00075-of-00093.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00075-of-00093.safetensors", + "model.layers.75.input_layernorm.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.0.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.0.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.0.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.1.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.1.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.1.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.10.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.10.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.10.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.100.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.100.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.100.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.101.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.101.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.101.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.102.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.102.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.102.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.103.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.103.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.103.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.104.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.104.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.104.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.105.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.105.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.105.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.106.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.106.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.106.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.107.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.107.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.107.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.108.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.108.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.108.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.109.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.109.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.109.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.11.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.11.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.11.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.110.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.110.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.110.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.111.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.111.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.111.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.112.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.112.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.112.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.113.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.113.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.113.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.114.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.114.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.114.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.115.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.115.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.115.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.116.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.116.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.116.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.117.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.117.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.117.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.118.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.118.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.118.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.119.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.119.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.119.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.12.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.12.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.12.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.120.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.120.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.120.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.121.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.121.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.121.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.122.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.122.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.122.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.123.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.123.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.123.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.124.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.124.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.124.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.125.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.125.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.125.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.126.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.126.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.126.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.127.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.127.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.127.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.128.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.128.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.128.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.129.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.129.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.129.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.13.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.13.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.13.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.130.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.130.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.130.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.131.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.131.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.131.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.132.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.132.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.132.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.133.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.133.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.133.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.134.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.134.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.134.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.135.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.135.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.135.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.136.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.136.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.136.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.137.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.137.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.137.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.138.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.138.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.138.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.139.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.139.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.139.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.14.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.14.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.14.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.140.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.140.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.140.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.141.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.141.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.141.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.142.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.142.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.142.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.143.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.143.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.143.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.144.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.144.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.144.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.145.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.145.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.145.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.146.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.146.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.146.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.147.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.147.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.147.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.148.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.148.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.148.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.149.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.149.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.149.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.15.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.15.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.15.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.150.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.150.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.150.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.151.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.151.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.151.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.152.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.152.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.152.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.153.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.153.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.153.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.154.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.154.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.154.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.155.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.155.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.155.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.156.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.156.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.156.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.157.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.157.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.157.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.158.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.158.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.158.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.159.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.159.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.159.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.16.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.16.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.16.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.17.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.17.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.17.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.18.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.18.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.18.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.19.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.19.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.19.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.2.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.2.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.2.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.20.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.20.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.20.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.21.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.21.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.21.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.22.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.22.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.22.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.23.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.23.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.23.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.24.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.24.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.24.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.25.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.25.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.25.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.26.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.26.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.26.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.27.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.27.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.27.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.28.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.28.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.28.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.29.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.29.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.29.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.3.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.3.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.3.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.30.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.30.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.30.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.31.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.31.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.31.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.32.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.32.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.32.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.33.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.33.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.33.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.34.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.34.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.34.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.35.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.35.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.35.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.36.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.36.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.36.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.37.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.37.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.37.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.38.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.38.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.38.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.39.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.39.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.39.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.4.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.4.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.4.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.40.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.40.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.40.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.41.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.41.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.41.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.42.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.42.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.42.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.43.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.43.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.43.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.44.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.44.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.44.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.45.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.45.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.45.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.46.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.46.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.46.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.47.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.47.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.47.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.48.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.48.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.48.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.49.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.49.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.49.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.5.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.5.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.5.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.50.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.50.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.50.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.51.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.51.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.51.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.52.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.52.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.52.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.53.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.53.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.53.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.54.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.54.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.54.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.55.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.55.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.55.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.56.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.56.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.56.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.57.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.57.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.57.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.58.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.58.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.58.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.59.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.59.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.59.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.6.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.6.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.6.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.60.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.60.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.60.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.61.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.61.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.61.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.62.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.62.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.62.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.63.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.63.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.63.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.64.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.64.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.64.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.65.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.65.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.65.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.66.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.66.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.66.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.67.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.67.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.67.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.68.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.68.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.68.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.69.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.69.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.69.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.7.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.7.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.7.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.70.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.70.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.70.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.71.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.71.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.71.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.72.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.72.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.72.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.73.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.73.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.73.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.74.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.74.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.74.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.75.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.75.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.75.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.76.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.76.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.76.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.77.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.77.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.77.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.78.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.78.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.78.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.79.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.79.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.79.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.8.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.8.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.8.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.80.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.80.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.80.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.81.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.81.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.81.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.82.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.82.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.82.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.83.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.83.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.83.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.84.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.84.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.84.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.85.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.85.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.85.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.86.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.86.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.86.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.87.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.87.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.87.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.88.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.88.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.88.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.89.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.89.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.89.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.9.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.9.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.9.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.90.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.90.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.90.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.91.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.91.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.91.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.92.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.92.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.92.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.93.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.93.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.93.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.94.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.94.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.94.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.95.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.95.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.95.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.96.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.96.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.96.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.97.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.97.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.97.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.98.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.98.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.98.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.99.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.99.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.experts.99.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.gate.e_score_correction_bias": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.gate.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.k_norm.weight": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.k_proj.bias": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.q_norm.weight": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.q_proj.bias": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.v_proj.bias": "model-00076-of-00093.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00076-of-00093.safetensors", + "model.layers.76.input_layernorm.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.0.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.0.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.0.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.1.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.1.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.1.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.10.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.10.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.10.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.100.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.100.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.100.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.101.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.101.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.101.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.102.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.102.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.102.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.103.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.103.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.103.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.104.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.104.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.104.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.105.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.105.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.105.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.106.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.106.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.106.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.107.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.107.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.107.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.108.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.108.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.108.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.109.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.109.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.109.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.11.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.11.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.11.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.110.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.110.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.110.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.111.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.111.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.111.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.112.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.112.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.112.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.113.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.113.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.113.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.114.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.114.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.114.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.115.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.115.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.115.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.116.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.116.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.116.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.117.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.117.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.117.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.118.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.118.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.118.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.119.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.119.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.119.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.12.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.12.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.12.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.120.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.120.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.120.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.121.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.121.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.121.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.122.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.122.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.122.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.123.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.123.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.123.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.124.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.124.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.124.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.125.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.125.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.125.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.126.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.126.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.126.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.127.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.127.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.127.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.128.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.128.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.128.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.129.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.129.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.129.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.13.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.13.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.13.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.130.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.130.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.130.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.131.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.131.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.131.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.132.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.132.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.132.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.133.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.133.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.133.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.134.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.134.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.134.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.135.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.135.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.135.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.136.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.136.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.136.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.137.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.137.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.137.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.138.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.138.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.138.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.139.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.139.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.139.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.14.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.14.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.14.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.140.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.140.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.140.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.141.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.141.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.141.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.142.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.142.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.142.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.143.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.143.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.143.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.144.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.144.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.144.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.145.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.145.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.145.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.146.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.146.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.146.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.147.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.147.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.147.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.148.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.148.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.148.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.149.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.149.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.149.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.15.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.15.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.15.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.150.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.150.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.150.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.151.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.151.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.151.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.152.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.152.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.152.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.153.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.153.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.153.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.154.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.154.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.154.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.155.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.155.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.155.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.156.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.156.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.156.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.157.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.157.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.157.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.158.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.158.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.158.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.159.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.159.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.159.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.16.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.16.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.16.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.17.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.17.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.17.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.18.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.18.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.18.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.19.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.19.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.19.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.2.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.2.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.2.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.20.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.20.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.20.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.21.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.21.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.21.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.22.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.22.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.22.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.23.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.23.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.23.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.24.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.24.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.24.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.25.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.25.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.25.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.26.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.26.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.26.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.27.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.27.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.27.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.28.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.28.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.28.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.29.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.29.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.29.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.3.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.3.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.3.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.30.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.30.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.30.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.31.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.31.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.31.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.32.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.32.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.32.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.33.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.33.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.33.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.34.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.34.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.34.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.35.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.35.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.35.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.36.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.36.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.36.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.37.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.37.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.37.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.38.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.38.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.38.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.39.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.39.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.39.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.4.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.4.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.4.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.40.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.40.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.40.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.41.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.41.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.41.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.42.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.42.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.42.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.43.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.43.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.43.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.44.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.44.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.44.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.45.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.45.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.45.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.46.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.46.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.46.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.47.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.47.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.47.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.48.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.48.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.48.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.49.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.49.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.49.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.5.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.5.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.5.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.50.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.50.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.50.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.51.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.51.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.51.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.52.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.52.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.52.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.53.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.53.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.53.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.54.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.54.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.54.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.55.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.55.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.55.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.56.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.56.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.56.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.57.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.57.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.57.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.58.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.58.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.58.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.59.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.59.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.59.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.6.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.6.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.6.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.60.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.60.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.60.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.61.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.61.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.61.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.62.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.62.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.62.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.63.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.63.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.63.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.64.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.64.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.64.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.65.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.65.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.65.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.66.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.66.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.66.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.67.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.67.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.67.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.68.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.68.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.68.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.69.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.69.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.69.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.7.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.7.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.7.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.70.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.70.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.70.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.71.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.71.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.71.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.72.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.72.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.72.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.73.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.73.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.73.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.74.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.74.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.74.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.75.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.75.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.75.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.76.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.76.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.76.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.77.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.77.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.77.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.78.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.78.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.78.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.79.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.79.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.79.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.8.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.8.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.8.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.80.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.80.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.80.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.81.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.81.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.81.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.82.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.82.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.82.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.83.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.83.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.83.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.84.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.84.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.84.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.85.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.85.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.85.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.86.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.86.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.86.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.87.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.87.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.87.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.88.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.88.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.88.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.89.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.89.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.89.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.9.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.9.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.9.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.90.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.90.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.90.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.91.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.91.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.91.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.92.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.92.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.92.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.93.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.93.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.93.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.94.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.94.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.94.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.95.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.95.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.95.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.96.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.96.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.96.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.97.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.97.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.97.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.98.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.98.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.98.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.99.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.99.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.experts.99.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.gate.e_score_correction_bias": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.gate.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.k_norm.weight": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.k_proj.bias": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.q_norm.weight": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.q_proj.bias": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.v_proj.bias": "model-00077-of-00093.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00077-of-00093.safetensors", + "model.layers.77.input_layernorm.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.0.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.0.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.0.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.1.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.1.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.1.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.10.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.10.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.10.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.100.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.100.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.100.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.101.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.101.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.101.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.102.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.102.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.102.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.103.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.103.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.103.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.104.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.104.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.104.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.105.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.105.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.105.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.106.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.106.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.106.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.107.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.107.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.107.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.108.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.108.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.108.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.109.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.109.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.109.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.11.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.11.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.11.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.110.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.110.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.110.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.111.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.111.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.111.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.112.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.112.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.112.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.113.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.113.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.113.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.114.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.114.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.114.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.115.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.115.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.115.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.116.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.116.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.116.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.117.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.117.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.117.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.118.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.118.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.118.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.119.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.119.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.119.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.12.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.12.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.12.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.120.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.120.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.120.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.121.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.121.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.121.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.122.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.122.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.122.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.123.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.123.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.123.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.124.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.124.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.124.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.125.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.125.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.125.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.126.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.126.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.126.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.127.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.127.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.127.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.128.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.128.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.128.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.129.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.129.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.129.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.13.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.13.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.13.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.130.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.130.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.130.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.131.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.131.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.131.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.132.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.132.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.132.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.133.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.133.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.133.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.134.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.134.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.134.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.135.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.135.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.135.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.136.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.136.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.136.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.137.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.137.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.137.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.138.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.138.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.138.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.139.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.139.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.139.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.14.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.14.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.14.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.140.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.140.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.140.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.141.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.141.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.141.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.142.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.142.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.142.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.143.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.143.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.143.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.144.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.144.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.144.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.145.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.145.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.145.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.146.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.146.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.146.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.147.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.147.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.147.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.148.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.148.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.148.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.149.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.149.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.149.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.15.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.15.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.15.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.150.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.150.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.150.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.151.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.151.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.151.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.152.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.152.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.152.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.153.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.153.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.153.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.154.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.154.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.154.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.155.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.155.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.155.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.156.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.156.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.156.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.157.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.157.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.157.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.158.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.158.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.158.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.159.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.159.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.159.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.16.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.16.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.16.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.17.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.17.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.17.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.18.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.18.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.18.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.19.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.19.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.19.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.2.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.2.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.2.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.20.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.20.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.20.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.21.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.21.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.21.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.22.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.22.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.22.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.23.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.23.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.23.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.24.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.24.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.24.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.25.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.25.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.25.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.26.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.26.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.26.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.27.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.27.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.27.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.28.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.28.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.28.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.29.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.29.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.29.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.3.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.3.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.3.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.30.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.30.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.30.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.31.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.31.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.31.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.32.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.32.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.32.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.33.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.33.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.33.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.34.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.34.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.34.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.35.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.35.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.35.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.36.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.36.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.36.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.37.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.37.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.37.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.38.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.38.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.38.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.39.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.39.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.39.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.4.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.4.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.4.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.40.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.40.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.40.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.41.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.41.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.41.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.42.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.42.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.42.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.43.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.43.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.43.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.44.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.44.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.44.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.45.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.45.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.45.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.46.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.46.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.46.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.47.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.47.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.47.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.48.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.48.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.48.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.49.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.49.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.49.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.5.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.5.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.5.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.50.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.50.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.50.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.51.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.51.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.51.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.52.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.52.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.52.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.53.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.53.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.53.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.54.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.54.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.54.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.55.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.55.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.55.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.56.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.56.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.56.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.57.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.57.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.57.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.58.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.58.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.58.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.59.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.59.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.59.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.6.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.6.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.6.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.60.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.60.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.60.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.61.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.61.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.61.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.62.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.62.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.62.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.63.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.63.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.63.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.64.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.64.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.64.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.65.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.65.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.65.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.66.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.66.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.66.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.67.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.67.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.67.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.68.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.68.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.68.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.69.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.69.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.69.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.7.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.7.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.7.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.70.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.70.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.70.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.71.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.71.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.71.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.72.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.72.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.72.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.73.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.73.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.73.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.74.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.74.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.74.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.75.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.75.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.75.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.76.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.76.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.76.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.77.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.77.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.77.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.78.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.78.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.78.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.79.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.79.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.79.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.8.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.8.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.8.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.80.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.80.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.80.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.81.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.81.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.81.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.82.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.82.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.82.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.83.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.83.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.83.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.84.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.84.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.84.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.85.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.85.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.85.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.86.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.86.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.86.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.87.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.87.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.87.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.88.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.88.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.88.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.89.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.89.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.89.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.9.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.9.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.9.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.90.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.90.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.90.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.91.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.91.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.91.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.92.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.92.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.92.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.93.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.93.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.93.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.94.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.94.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.94.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.95.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.95.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.95.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.96.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.96.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.96.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.97.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.97.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.97.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.98.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.98.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.98.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.99.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.99.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.experts.99.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.gate.e_score_correction_bias": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.gate.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.k_norm.weight": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.k_proj.bias": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.q_norm.weight": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.q_proj.bias": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.v_proj.bias": "model-00078-of-00093.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00078-of-00093.safetensors", + "model.layers.78.input_layernorm.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.0.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.0.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.0.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.1.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.1.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.1.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.10.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.10.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.10.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.100.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.100.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.100.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.101.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.101.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.101.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.102.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.102.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.102.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.103.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.103.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.103.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.104.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.104.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.104.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.105.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.105.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.105.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.106.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.106.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.106.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.107.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.107.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.107.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.108.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.108.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.108.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.109.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.109.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.109.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.11.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.11.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.11.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.110.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.110.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.110.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.111.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.111.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.111.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.112.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.112.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.112.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.113.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.113.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.113.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.114.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.114.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.114.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.115.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.115.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.115.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.116.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.116.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.116.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.117.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.117.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.117.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.118.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.118.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.118.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.119.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.119.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.119.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.12.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.12.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.12.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.120.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.120.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.120.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.121.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.121.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.121.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.122.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.122.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.122.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.123.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.123.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.123.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.124.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.124.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.124.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.125.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.125.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.125.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.126.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.126.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.126.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.127.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.127.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.127.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.128.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.128.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.128.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.129.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.129.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.129.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.13.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.13.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.13.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.130.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.130.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.130.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.131.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.131.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.131.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.132.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.132.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.132.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.133.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.133.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.133.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.134.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.134.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.134.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.135.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.135.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.135.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.136.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.136.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.136.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.137.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.137.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.137.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.138.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.138.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.138.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.139.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.139.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.139.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.14.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.14.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.14.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.140.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.140.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.140.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.141.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.141.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.141.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.142.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.142.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.142.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.143.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.143.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.143.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.144.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.144.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.144.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.145.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.145.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.145.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.146.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.146.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.146.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.147.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.147.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.147.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.148.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.148.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.148.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.149.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.149.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.149.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.15.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.15.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.15.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.150.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.150.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.150.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.151.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.151.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.151.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.152.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.152.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.152.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.153.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.153.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.153.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.154.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.154.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.154.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.155.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.155.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.155.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.156.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.156.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.156.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.157.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.157.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.157.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.158.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.158.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.158.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.159.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.159.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.159.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.16.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.16.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.16.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.17.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.17.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.17.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.18.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.18.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.18.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.19.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.19.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.19.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.2.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.2.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.2.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.20.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.20.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.20.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.21.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.21.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.21.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.22.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.22.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.22.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.23.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.23.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.23.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.24.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.24.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.24.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.25.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.25.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.25.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.26.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.26.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.26.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.27.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.27.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.27.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.28.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.28.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.28.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.29.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.29.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.29.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.3.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.3.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.3.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.30.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.30.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.30.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.31.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.31.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.31.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.32.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.32.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.32.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.33.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.33.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.33.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.34.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.34.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.34.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.35.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.35.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.35.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.36.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.36.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.36.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.37.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.37.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.37.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.38.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.38.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.38.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.39.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.39.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.39.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.4.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.4.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.4.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.40.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.40.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.40.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.41.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.41.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.41.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.42.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.42.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.42.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.43.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.43.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.43.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.44.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.44.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.44.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.45.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.45.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.45.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.46.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.46.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.46.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.47.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.47.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.47.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.48.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.48.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.48.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.49.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.49.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.49.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.5.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.5.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.5.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.50.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.50.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.50.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.51.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.51.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.51.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.52.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.52.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.52.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.53.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.53.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.53.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.54.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.54.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.54.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.55.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.55.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.55.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.56.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.56.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.56.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.57.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.57.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.57.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.58.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.58.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.58.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.59.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.59.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.59.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.6.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.6.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.6.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.60.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.60.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.60.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.61.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.61.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.61.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.62.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.62.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.62.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.63.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.63.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.63.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.64.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.64.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.64.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.65.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.65.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.65.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.66.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.66.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.66.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.67.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.67.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.67.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.68.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.68.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.68.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.69.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.69.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.69.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.7.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.7.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.7.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.70.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.70.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.70.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.71.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.71.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.71.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.72.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.72.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.72.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.73.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.73.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.73.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.74.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.74.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.74.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.75.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.75.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.75.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.76.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.76.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.76.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.77.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.77.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.77.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.78.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.78.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.78.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.79.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.79.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.79.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.8.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.8.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.8.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.80.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.80.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.80.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.81.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.81.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.81.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.82.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.82.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.82.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.83.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.83.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.83.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.84.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.84.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.84.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.85.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.85.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.85.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.86.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.86.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.86.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.87.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.87.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.87.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.88.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.88.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.88.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.89.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.89.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.89.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.9.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.9.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.9.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.90.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.90.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.90.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.91.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.91.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.91.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.92.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.92.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.92.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.93.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.93.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.93.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.94.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.94.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.94.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.95.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.95.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.95.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.96.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.96.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.96.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.97.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.97.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.97.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.98.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.98.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.98.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.99.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.99.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.experts.99.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.gate.e_score_correction_bias": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.gate.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.k_norm.weight": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.k_proj.bias": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.q_norm.weight": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.q_proj.bias": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.v_proj.bias": "model-00079-of-00093.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00079-of-00093.safetensors", + "model.layers.79.input_layernorm.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.0.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.0.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.0.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.1.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.1.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.1.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.10.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.10.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.10.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.100.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.100.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.100.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.101.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.101.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.101.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.102.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.102.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.102.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.103.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.103.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.103.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.104.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.104.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.104.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.105.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.105.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.105.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.106.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.106.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.106.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.107.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.107.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.107.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.108.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.108.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.108.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.109.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.109.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.109.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.11.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.11.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.11.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.110.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.110.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.110.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.111.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.111.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.111.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.112.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.112.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.112.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.113.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.113.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.113.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.114.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.114.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.114.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.115.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.115.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.115.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.116.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.116.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.116.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.117.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.117.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.117.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.118.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.118.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.118.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.119.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.119.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.119.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.12.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.12.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.12.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.120.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.120.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.120.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.121.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.121.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.121.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.122.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.122.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.122.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.123.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.123.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.123.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.124.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.124.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.124.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.125.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.125.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.125.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.126.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.126.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.126.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.127.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.127.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.127.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.128.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.128.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.128.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.129.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.129.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.129.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.13.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.13.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.13.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.130.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.130.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.130.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.131.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.131.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.131.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.132.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.132.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.132.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.133.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.133.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.133.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.134.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.134.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.134.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.135.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.135.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.135.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.136.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.136.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.136.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.137.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.137.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.137.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.138.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.138.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.138.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.139.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.139.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.139.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.14.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.14.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.14.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.140.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.140.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.140.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.141.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.141.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.141.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.142.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.142.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.142.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.143.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.143.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.143.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.144.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.144.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.144.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.145.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.145.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.145.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.146.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.146.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.146.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.147.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.147.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.147.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.148.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.148.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.148.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.149.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.149.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.149.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.15.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.15.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.15.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.150.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.150.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.150.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.151.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.151.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.151.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.152.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.152.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.152.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.153.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.153.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.153.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.154.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.154.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.154.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.155.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.155.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.155.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.156.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.156.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.156.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.157.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.157.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.157.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.158.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.158.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.158.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.159.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.159.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.159.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.16.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.16.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.16.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.17.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.17.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.17.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.18.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.18.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.18.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.19.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.19.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.19.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.2.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.2.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.2.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.20.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.20.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.20.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.21.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.21.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.21.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.22.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.22.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.22.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.23.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.23.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.23.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.24.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.24.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.24.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.25.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.25.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.25.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.26.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.26.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.26.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.27.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.27.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.27.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.28.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.28.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.28.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.29.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.29.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.29.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.3.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.3.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.3.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.30.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.30.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.30.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.31.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.31.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.31.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.32.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.32.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.32.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.33.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.33.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.33.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.34.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.34.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.34.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.35.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.35.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.35.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.36.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.36.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.36.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.37.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.37.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.37.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.38.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.38.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.38.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.39.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.39.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.39.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.4.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.4.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.4.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.40.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.40.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.40.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.41.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.41.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.41.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.42.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.42.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.42.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.43.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.43.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.43.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.44.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.44.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.44.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.45.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.45.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.45.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.46.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.46.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.46.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.47.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.47.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.47.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.48.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.48.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.48.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.49.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.49.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.49.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.5.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.5.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.5.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.50.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.50.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.50.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.51.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.51.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.51.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.52.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.52.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.52.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.53.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.53.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.53.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.54.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.54.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.54.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.55.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.55.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.55.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.56.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.56.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.56.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.57.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.57.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.57.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.58.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.58.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.58.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.59.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.59.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.59.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.6.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.6.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.6.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.60.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.60.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.60.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.61.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.61.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.61.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.62.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.62.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.62.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.63.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.63.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.63.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.64.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.64.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.64.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.65.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.65.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.65.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.66.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.66.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.66.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.67.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.67.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.67.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.68.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.68.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.68.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.69.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.69.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.69.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.7.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.7.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.7.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.70.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.70.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.70.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.71.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.71.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.71.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.72.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.72.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.72.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.73.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.73.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.73.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.74.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.74.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.74.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.75.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.75.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.75.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.76.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.76.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.76.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.77.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.77.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.77.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.78.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.78.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.78.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.79.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.79.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.79.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.8.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.8.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.8.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.80.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.80.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.80.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.81.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.81.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.81.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.82.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.82.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.82.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.83.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.83.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.83.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.84.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.84.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.84.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.85.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.85.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.85.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.86.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.86.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.86.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.87.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.87.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.87.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.88.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.88.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.88.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.89.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.89.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.89.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.9.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.9.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.9.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.90.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.90.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.90.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.91.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.91.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.91.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.92.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.92.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.92.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.93.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.93.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.93.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.94.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.94.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.94.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.95.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.95.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.95.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.96.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.96.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.96.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.97.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.97.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.97.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.98.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.98.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.98.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.99.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.99.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.experts.99.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.gate.e_score_correction_bias": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.gate.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.k_norm.weight": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.k_proj.bias": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.q_norm.weight": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.q_proj.bias": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.v_proj.bias": "model-00080-of-00093.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00080-of-00093.safetensors", + "model.layers.80.input_layernorm.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.0.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.0.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.0.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.1.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.1.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.1.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.10.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.10.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.10.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.100.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.100.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.100.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.101.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.101.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.101.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.102.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.102.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.102.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.103.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.103.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.103.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.104.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.104.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.104.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.105.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.105.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.105.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.106.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.106.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.106.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.107.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.107.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.107.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.108.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.108.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.108.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.109.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.109.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.109.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.11.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.11.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.11.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.110.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.110.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.110.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.111.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.111.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.111.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.112.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.112.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.112.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.113.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.113.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.113.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.114.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.114.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.114.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.115.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.115.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.115.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.116.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.116.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.116.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.117.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.117.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.117.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.118.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.118.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.118.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.119.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.119.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.119.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.12.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.12.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.12.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.120.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.120.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.120.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.121.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.121.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.121.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.122.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.122.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.122.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.123.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.123.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.123.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.124.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.124.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.124.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.125.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.125.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.125.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.126.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.126.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.126.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.127.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.127.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.127.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.128.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.128.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.128.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.129.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.129.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.129.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.13.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.13.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.13.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.130.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.130.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.130.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.131.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.131.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.131.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.132.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.132.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.132.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.133.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.133.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.133.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.134.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.134.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.134.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.135.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.135.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.135.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.136.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.136.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.136.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.137.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.137.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.137.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.138.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.138.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.138.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.139.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.139.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.139.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.14.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.14.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.14.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.140.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.140.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.140.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.141.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.141.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.141.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.142.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.142.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.142.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.143.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.143.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.143.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.144.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.144.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.144.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.145.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.145.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.145.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.146.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.146.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.146.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.147.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.147.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.147.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.148.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.148.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.148.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.149.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.149.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.149.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.15.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.15.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.15.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.150.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.150.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.150.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.151.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.151.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.151.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.152.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.152.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.152.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.153.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.153.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.153.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.154.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.154.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.154.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.155.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.155.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.155.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.156.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.156.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.156.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.157.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.157.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.157.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.158.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.158.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.158.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.159.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.159.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.159.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.16.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.16.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.16.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.17.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.17.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.17.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.18.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.18.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.18.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.19.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.19.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.19.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.2.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.2.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.2.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.20.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.20.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.20.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.21.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.21.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.21.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.22.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.22.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.22.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.23.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.23.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.23.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.24.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.24.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.24.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.25.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.25.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.25.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.26.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.26.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.26.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.27.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.27.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.27.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.28.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.28.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.28.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.29.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.29.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.29.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.3.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.3.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.3.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.30.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.30.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.30.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.31.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.31.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.31.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.32.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.32.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.32.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.33.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.33.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.33.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.34.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.34.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.34.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.35.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.35.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.35.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.36.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.36.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.36.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.37.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.37.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.37.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.38.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.38.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.38.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.39.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.39.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.39.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.4.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.4.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.4.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.40.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.40.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.40.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.41.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.41.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.41.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.42.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.42.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.42.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.43.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.43.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.43.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.44.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.44.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.44.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.45.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.45.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.45.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.46.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.46.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.46.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.47.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.47.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.47.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.48.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.48.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.48.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.49.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.49.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.49.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.5.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.5.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.5.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.50.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.50.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.50.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.51.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.51.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.51.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.52.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.52.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.52.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.53.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.53.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.53.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.54.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.54.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.54.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.55.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.55.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.55.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.56.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.56.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.56.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.57.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.57.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.57.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.58.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.58.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.58.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.59.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.59.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.59.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.6.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.6.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.6.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.60.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.60.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.60.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.61.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.61.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.61.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.62.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.62.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.62.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.63.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.63.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.63.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.64.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.64.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.64.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.65.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.65.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.65.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.66.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.66.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.66.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.67.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.67.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.67.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.68.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.68.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.68.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.69.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.69.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.69.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.7.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.7.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.7.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.70.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.70.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.70.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.71.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.71.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.71.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.72.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.72.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.72.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.73.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.73.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.73.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.74.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.74.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.74.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.75.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.75.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.75.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.76.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.76.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.76.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.77.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.77.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.77.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.78.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.78.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.78.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.79.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.79.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.79.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.8.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.8.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.8.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.80.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.80.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.80.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.81.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.81.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.81.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.82.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.82.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.82.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.83.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.83.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.83.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.84.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.84.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.84.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.85.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.85.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.85.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.86.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.86.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.86.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.87.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.87.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.87.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.88.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.88.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.88.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.89.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.89.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.89.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.9.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.9.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.9.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.90.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.90.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.90.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.91.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.91.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.91.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.92.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.92.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.92.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.93.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.93.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.93.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.94.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.94.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.94.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.95.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.95.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.95.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.96.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.96.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.96.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.97.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.97.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.97.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.98.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.98.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.98.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.99.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.99.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.experts.99.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.gate.e_score_correction_bias": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.gate.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.k_norm.weight": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.k_proj.bias": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.q_norm.weight": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.q_proj.bias": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.v_proj.bias": "model-00081-of-00093.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00081-of-00093.safetensors", + "model.layers.81.input_layernorm.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.0.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.0.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.0.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.1.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.1.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.1.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.10.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.10.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.10.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.100.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.100.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.100.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.101.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.101.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.101.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.102.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.102.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.102.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.103.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.103.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.103.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.104.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.104.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.104.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.105.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.105.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.105.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.106.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.106.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.106.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.107.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.107.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.107.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.108.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.108.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.108.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.109.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.109.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.109.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.11.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.11.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.11.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.110.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.110.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.110.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.111.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.111.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.111.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.112.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.112.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.112.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.113.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.113.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.113.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.114.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.114.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.114.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.115.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.115.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.115.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.116.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.116.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.116.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.117.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.117.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.117.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.118.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.118.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.118.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.119.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.119.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.119.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.12.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.12.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.12.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.120.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.120.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.120.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.121.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.121.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.121.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.122.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.122.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.122.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.123.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.123.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.123.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.124.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.124.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.124.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.125.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.125.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.125.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.126.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.126.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.126.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.127.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.127.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.127.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.128.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.128.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.128.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.129.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.129.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.129.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.13.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.13.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.13.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.130.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.130.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.130.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.131.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.131.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.131.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.132.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.132.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.132.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.133.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.133.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.133.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.134.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.134.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.134.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.135.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.135.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.135.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.136.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.136.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.136.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.137.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.137.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.137.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.138.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.138.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.138.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.139.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.139.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.139.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.14.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.14.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.14.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.140.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.140.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.140.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.141.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.141.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.141.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.142.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.142.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.142.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.143.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.143.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.143.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.144.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.144.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.144.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.145.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.145.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.145.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.146.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.146.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.146.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.147.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.147.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.147.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.148.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.148.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.148.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.149.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.149.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.149.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.15.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.15.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.15.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.150.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.150.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.150.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.151.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.151.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.151.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.152.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.152.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.152.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.153.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.153.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.153.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.154.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.154.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.154.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.155.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.155.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.155.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.156.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.156.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.156.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.157.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.157.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.157.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.158.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.158.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.158.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.159.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.159.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.159.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.16.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.16.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.16.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.17.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.17.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.17.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.18.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.18.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.18.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.19.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.19.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.19.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.2.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.2.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.2.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.20.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.20.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.20.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.21.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.21.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.21.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.22.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.22.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.22.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.23.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.23.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.23.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.24.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.24.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.24.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.25.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.25.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.25.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.26.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.26.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.26.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.27.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.27.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.27.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.28.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.28.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.28.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.29.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.29.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.29.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.3.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.3.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.3.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.30.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.30.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.30.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.31.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.31.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.31.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.32.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.32.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.32.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.33.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.33.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.33.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.34.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.34.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.34.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.35.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.35.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.35.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.36.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.36.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.36.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.37.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.37.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.37.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.38.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.38.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.38.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.39.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.39.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.39.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.4.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.4.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.4.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.40.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.40.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.40.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.41.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.41.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.41.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.42.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.42.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.42.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.43.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.43.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.43.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.44.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.44.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.44.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.45.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.45.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.45.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.46.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.46.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.46.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.47.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.47.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.47.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.48.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.48.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.48.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.49.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.49.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.49.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.5.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.5.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.5.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.50.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.50.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.50.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.51.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.51.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.51.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.52.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.52.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.52.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.53.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.53.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.53.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.54.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.54.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.54.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.55.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.55.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.55.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.56.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.56.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.56.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.57.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.57.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.57.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.58.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.58.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.58.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.59.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.59.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.59.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.6.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.6.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.6.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.60.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.60.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.60.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.61.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.61.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.61.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.62.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.62.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.62.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.63.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.63.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.63.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.64.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.64.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.64.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.65.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.65.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.65.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.66.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.66.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.66.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.67.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.67.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.67.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.68.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.68.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.68.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.69.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.69.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.69.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.7.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.7.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.7.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.70.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.70.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.70.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.71.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.71.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.71.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.72.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.72.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.72.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.73.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.73.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.73.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.74.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.74.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.74.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.75.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.75.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.75.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.76.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.76.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.76.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.77.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.77.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.77.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.78.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.78.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.78.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.79.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.79.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.79.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.8.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.8.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.8.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.80.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.80.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.80.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.81.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.81.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.81.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.82.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.82.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.82.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.83.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.83.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.83.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.84.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.84.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.84.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.85.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.85.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.85.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.86.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.86.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.86.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.87.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.87.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.87.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.88.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.88.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.88.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.89.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.89.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.89.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.9.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.9.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.9.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.90.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.90.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.90.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.91.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.91.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.91.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.92.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.92.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.92.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.93.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.93.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.93.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.94.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.94.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.94.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.95.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.95.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.95.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.96.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.96.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.96.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.97.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.97.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.97.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.98.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.98.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.98.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.99.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.99.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.experts.99.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.gate.e_score_correction_bias": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.gate.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.k_norm.weight": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.k_proj.bias": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.q_norm.weight": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.q_proj.bias": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.v_proj.bias": "model-00082-of-00093.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00082-of-00093.safetensors", + "model.layers.82.input_layernorm.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.0.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.0.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.0.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.1.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.1.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.1.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.10.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.10.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.10.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.100.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.100.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.100.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.101.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.101.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.101.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.102.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.102.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.102.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.103.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.103.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.103.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.104.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.104.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.104.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.105.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.105.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.105.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.106.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.106.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.106.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.107.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.107.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.107.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.108.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.108.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.108.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.109.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.109.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.109.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.11.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.11.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.11.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.110.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.110.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.110.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.111.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.111.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.111.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.112.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.112.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.112.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.113.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.113.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.113.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.114.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.114.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.114.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.115.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.115.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.115.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.116.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.116.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.116.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.117.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.117.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.117.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.118.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.118.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.118.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.119.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.119.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.119.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.12.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.12.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.12.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.120.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.120.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.120.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.121.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.121.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.121.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.122.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.122.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.122.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.123.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.123.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.123.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.124.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.124.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.124.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.125.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.125.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.125.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.126.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.126.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.126.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.127.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.127.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.127.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.128.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.128.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.128.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.129.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.129.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.129.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.13.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.13.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.13.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.130.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.130.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.130.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.131.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.131.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.131.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.132.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.132.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.132.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.133.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.133.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.133.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.134.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.134.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.134.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.135.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.135.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.135.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.136.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.136.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.136.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.137.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.137.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.137.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.138.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.138.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.138.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.139.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.139.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.139.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.14.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.14.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.14.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.140.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.140.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.140.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.141.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.141.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.141.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.142.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.142.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.142.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.143.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.143.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.143.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.144.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.144.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.144.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.145.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.145.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.145.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.146.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.146.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.146.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.147.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.147.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.147.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.148.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.148.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.148.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.149.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.149.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.149.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.15.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.15.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.15.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.150.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.150.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.150.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.151.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.151.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.151.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.152.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.152.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.152.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.153.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.153.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.153.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.154.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.154.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.154.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.155.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.155.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.155.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.156.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.156.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.156.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.157.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.157.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.157.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.158.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.158.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.158.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.159.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.159.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.159.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.16.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.16.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.16.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.17.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.17.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.17.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.18.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.18.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.18.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.19.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.19.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.19.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.2.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.2.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.2.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.20.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.20.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.20.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.21.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.21.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.21.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.22.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.22.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.22.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.23.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.23.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.23.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.24.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.24.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.24.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.25.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.25.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.25.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.26.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.26.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.26.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.27.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.27.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.27.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.28.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.28.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.28.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.29.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.29.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.29.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.3.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.3.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.3.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.30.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.30.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.30.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.31.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.31.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.31.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.32.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.32.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.32.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.33.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.33.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.33.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.34.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.34.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.34.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.35.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.35.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.35.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.36.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.36.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.36.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.37.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.37.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.37.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.38.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.38.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.38.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.39.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.39.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.39.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.4.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.4.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.4.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.40.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.40.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.40.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.41.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.41.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.41.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.42.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.42.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.42.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.43.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.43.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.43.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.44.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.44.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.44.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.45.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.45.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.45.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.46.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.46.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.46.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.47.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.47.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.47.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.48.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.48.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.48.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.49.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.49.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.49.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.5.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.5.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.5.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.50.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.50.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.50.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.51.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.51.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.51.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.52.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.52.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.52.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.53.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.53.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.53.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.54.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.54.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.54.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.55.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.55.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.55.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.56.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.56.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.56.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.57.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.57.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.57.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.58.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.58.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.58.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.59.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.59.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.59.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.6.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.6.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.6.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.60.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.60.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.60.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.61.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.61.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.61.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.62.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.62.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.62.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.63.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.63.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.63.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.64.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.64.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.64.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.65.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.65.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.65.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.66.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.66.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.66.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.67.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.67.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.67.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.68.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.68.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.68.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.69.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.69.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.69.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.7.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.7.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.7.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.70.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.70.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.70.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.71.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.71.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.71.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.72.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.72.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.72.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.73.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.73.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.73.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.74.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.74.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.74.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.75.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.75.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.75.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.76.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.76.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.76.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.77.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.77.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.77.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.78.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.78.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.78.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.79.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.79.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.79.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.8.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.8.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.8.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.80.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.80.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.80.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.81.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.81.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.81.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.82.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.82.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.82.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.83.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.83.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.83.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.84.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.84.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.84.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.85.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.85.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.85.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.86.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.86.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.86.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.87.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.87.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.87.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.88.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.88.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.88.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.89.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.89.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.89.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.9.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.9.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.9.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.90.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.90.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.90.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.91.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.91.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.91.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.92.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.92.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.92.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.93.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.93.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.93.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.94.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.94.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.94.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.95.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.95.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.95.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.96.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.96.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.96.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.97.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.97.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.97.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.98.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.98.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.98.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.99.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.99.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.experts.99.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.gate.e_score_correction_bias": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.gate.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.k_norm.weight": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.k_proj.bias": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.q_norm.weight": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.q_proj.bias": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.v_proj.bias": "model-00083-of-00093.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00083-of-00093.safetensors", + "model.layers.83.input_layernorm.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.0.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.0.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.0.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.1.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.1.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.1.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.10.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.10.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.10.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.100.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.100.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.100.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.101.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.101.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.101.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.102.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.102.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.102.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.103.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.103.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.103.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.104.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.104.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.104.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.105.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.105.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.105.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.106.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.106.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.106.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.107.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.107.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.107.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.108.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.108.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.108.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.109.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.109.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.109.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.11.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.11.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.11.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.110.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.110.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.110.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.111.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.111.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.111.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.112.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.112.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.112.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.113.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.113.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.113.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.114.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.114.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.114.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.115.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.115.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.115.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.116.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.116.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.116.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.117.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.117.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.117.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.118.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.118.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.118.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.119.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.119.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.119.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.12.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.12.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.12.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.120.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.120.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.120.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.121.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.121.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.121.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.122.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.122.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.122.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.123.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.123.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.123.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.124.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.124.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.124.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.125.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.125.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.125.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.126.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.126.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.126.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.127.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.127.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.127.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.128.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.128.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.128.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.129.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.129.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.129.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.13.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.13.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.13.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.130.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.130.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.130.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.131.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.131.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.131.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.132.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.132.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.132.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.133.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.133.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.133.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.134.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.134.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.134.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.135.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.135.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.135.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.136.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.136.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.136.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.137.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.137.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.137.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.138.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.138.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.138.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.139.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.139.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.139.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.14.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.14.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.14.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.140.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.140.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.140.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.141.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.141.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.141.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.142.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.142.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.142.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.143.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.143.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.143.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.144.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.144.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.144.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.145.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.145.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.145.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.146.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.146.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.146.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.147.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.147.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.147.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.148.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.148.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.148.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.149.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.149.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.149.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.15.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.15.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.15.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.150.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.150.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.150.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.151.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.151.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.151.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.152.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.152.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.152.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.153.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.153.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.153.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.154.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.154.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.154.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.155.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.155.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.155.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.156.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.156.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.156.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.157.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.157.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.157.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.158.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.158.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.158.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.159.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.159.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.159.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.16.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.16.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.16.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.17.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.17.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.17.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.18.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.18.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.18.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.19.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.19.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.19.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.2.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.2.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.2.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.20.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.20.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.20.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.21.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.21.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.21.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.22.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.22.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.22.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.23.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.23.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.23.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.24.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.24.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.24.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.25.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.25.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.25.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.26.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.26.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.26.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.27.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.27.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.27.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.28.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.28.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.28.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.29.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.29.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.29.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.3.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.3.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.3.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.30.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.30.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.30.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.31.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.31.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.31.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.32.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.32.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.32.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.33.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.33.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.33.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.34.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.34.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.34.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.35.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.35.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.35.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.36.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.36.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.36.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.37.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.37.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.37.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.38.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.38.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.38.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.39.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.39.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.39.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.4.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.4.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.4.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.40.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.40.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.40.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.41.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.41.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.41.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.42.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.42.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.42.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.43.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.43.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.43.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.44.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.44.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.44.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.45.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.45.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.45.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.46.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.46.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.46.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.47.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.47.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.47.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.48.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.48.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.48.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.49.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.49.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.49.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.5.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.5.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.5.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.50.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.50.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.50.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.51.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.51.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.51.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.52.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.52.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.52.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.53.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.53.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.53.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.54.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.54.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.54.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.55.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.55.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.55.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.56.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.56.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.56.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.57.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.57.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.57.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.58.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.58.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.58.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.59.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.59.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.59.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.6.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.6.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.6.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.60.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.60.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.60.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.61.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.61.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.61.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.62.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.62.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.62.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.63.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.63.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.63.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.64.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.64.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.64.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.65.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.65.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.65.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.66.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.66.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.66.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.67.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.67.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.67.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.68.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.68.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.68.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.69.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.69.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.69.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.7.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.7.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.7.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.70.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.70.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.70.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.71.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.71.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.71.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.72.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.72.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.72.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.73.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.73.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.73.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.74.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.74.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.74.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.75.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.75.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.75.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.76.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.76.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.76.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.77.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.77.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.77.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.78.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.78.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.78.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.79.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.79.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.79.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.8.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.8.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.8.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.80.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.80.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.80.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.81.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.81.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.81.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.82.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.82.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.82.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.83.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.83.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.83.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.84.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.84.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.84.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.85.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.85.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.85.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.86.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.86.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.86.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.87.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.87.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.87.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.88.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.88.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.88.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.89.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.89.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.89.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.9.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.9.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.9.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.90.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.90.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.90.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.91.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.91.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.91.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.92.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.92.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.92.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.93.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.93.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.93.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.94.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.94.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.94.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.95.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.95.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.95.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.96.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.96.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.96.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.97.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.97.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.97.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.98.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.98.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.98.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.99.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.99.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.experts.99.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.gate.e_score_correction_bias": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.gate.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.k_norm.weight": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.k_proj.bias": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.q_norm.weight": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.q_proj.bias": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.v_proj.bias": "model-00084-of-00093.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00084-of-00093.safetensors", + "model.layers.84.input_layernorm.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.0.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.0.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.0.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.1.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.1.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.1.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.10.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.10.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.10.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.100.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.100.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.100.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.101.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.101.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.101.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.102.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.102.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.102.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.103.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.103.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.103.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.104.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.104.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.104.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.105.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.105.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.105.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.106.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.106.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.106.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.107.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.107.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.107.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.108.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.108.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.108.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.109.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.109.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.109.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.11.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.11.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.11.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.110.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.110.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.110.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.111.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.111.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.111.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.112.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.112.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.112.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.113.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.113.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.113.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.114.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.114.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.114.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.115.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.115.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.115.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.116.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.116.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.116.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.117.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.117.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.117.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.118.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.118.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.118.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.119.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.119.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.119.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.12.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.12.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.12.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.120.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.120.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.120.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.121.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.121.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.121.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.122.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.122.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.122.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.123.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.123.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.123.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.124.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.124.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.124.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.125.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.125.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.125.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.126.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.126.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.126.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.127.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.127.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.127.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.128.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.128.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.128.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.129.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.129.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.129.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.13.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.13.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.13.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.130.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.130.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.130.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.131.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.131.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.131.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.132.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.132.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.132.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.133.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.133.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.133.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.134.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.134.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.134.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.135.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.135.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.135.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.136.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.136.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.136.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.137.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.137.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.137.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.138.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.138.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.138.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.139.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.139.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.139.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.14.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.14.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.14.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.140.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.140.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.140.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.141.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.141.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.141.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.142.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.142.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.142.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.143.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.143.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.143.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.144.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.144.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.144.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.145.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.145.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.145.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.146.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.146.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.146.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.147.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.147.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.147.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.148.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.148.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.148.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.149.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.149.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.149.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.15.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.15.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.15.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.150.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.150.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.150.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.151.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.151.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.151.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.152.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.152.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.152.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.153.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.153.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.153.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.154.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.154.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.154.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.155.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.155.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.155.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.156.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.156.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.156.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.157.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.157.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.157.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.158.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.158.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.158.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.159.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.159.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.159.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.16.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.16.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.16.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.17.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.17.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.17.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.18.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.18.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.18.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.19.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.19.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.19.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.2.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.2.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.2.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.20.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.20.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.20.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.21.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.21.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.21.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.22.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.22.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.22.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.23.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.23.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.23.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.24.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.24.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.24.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.25.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.25.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.25.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.26.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.26.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.26.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.27.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.27.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.27.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.28.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.28.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.28.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.29.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.29.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.29.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.3.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.3.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.3.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.30.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.30.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.30.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.31.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.31.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.31.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.32.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.32.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.32.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.33.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.33.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.33.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.34.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.34.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.34.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.35.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.35.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.35.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.36.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.36.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.36.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.37.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.37.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.37.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.38.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.38.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.38.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.39.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.39.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.39.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.4.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.4.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.4.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.40.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.40.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.40.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.41.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.41.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.41.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.42.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.42.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.42.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.43.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.43.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.43.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.44.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.44.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.44.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.45.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.45.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.45.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.46.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.46.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.46.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.47.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.47.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.47.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.48.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.48.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.48.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.49.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.49.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.49.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.5.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.5.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.5.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.50.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.50.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.50.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.51.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.51.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.51.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.52.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.52.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.52.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.53.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.53.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.53.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.54.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.54.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.54.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.55.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.55.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.55.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.56.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.56.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.56.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.57.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.57.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.57.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.58.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.58.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.58.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.59.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.59.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.59.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.6.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.6.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.6.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.60.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.60.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.60.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.61.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.61.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.61.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.62.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.62.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.62.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.63.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.63.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.63.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.64.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.64.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.64.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.65.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.65.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.65.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.66.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.66.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.66.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.67.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.67.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.67.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.68.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.68.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.68.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.69.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.69.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.69.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.7.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.7.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.7.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.70.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.70.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.70.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.71.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.71.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.71.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.72.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.72.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.72.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.73.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.73.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.73.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.74.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.74.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.74.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.75.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.75.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.75.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.76.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.76.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.76.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.77.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.77.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.77.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.78.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.78.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.78.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.79.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.79.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.79.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.8.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.8.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.8.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.80.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.80.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.80.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.81.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.81.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.81.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.82.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.82.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.82.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.83.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.83.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.83.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.84.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.84.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.84.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.85.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.85.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.85.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.86.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.86.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.86.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.87.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.87.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.87.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.88.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.88.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.88.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.89.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.89.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.89.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.9.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.9.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.9.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.90.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.90.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.90.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.91.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.91.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.91.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.92.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.92.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.92.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.93.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.93.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.93.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.94.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.94.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.94.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.95.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.95.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.95.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.96.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.96.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.96.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.97.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.97.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.97.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.98.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.98.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.98.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.99.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.99.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.experts.99.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.gate.e_score_correction_bias": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.gate.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.k_norm.weight": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.k_proj.bias": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.q_norm.weight": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.q_proj.bias": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.v_proj.bias": "model-00085-of-00093.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00085-of-00093.safetensors", + "model.layers.85.input_layernorm.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.0.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.0.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.0.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.1.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.1.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.1.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.10.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.10.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.10.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.100.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.100.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.100.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.101.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.101.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.101.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.102.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.102.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.102.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.103.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.103.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.103.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.104.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.104.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.104.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.105.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.105.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.105.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.106.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.106.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.106.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.107.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.107.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.107.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.108.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.108.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.108.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.109.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.109.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.109.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.11.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.11.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.11.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.110.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.110.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.110.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.111.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.111.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.111.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.112.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.112.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.112.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.113.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.113.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.113.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.114.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.114.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.114.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.115.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.115.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.115.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.116.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.116.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.116.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.117.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.117.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.117.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.118.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.118.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.118.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.119.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.119.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.119.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.12.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.12.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.12.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.120.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.120.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.120.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.121.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.121.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.121.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.122.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.122.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.122.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.123.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.123.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.123.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.124.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.124.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.124.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.125.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.125.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.125.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.126.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.126.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.126.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.127.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.127.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.127.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.128.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.128.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.128.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.129.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.129.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.129.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.13.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.13.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.13.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.130.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.130.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.130.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.131.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.131.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.131.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.132.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.132.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.132.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.133.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.133.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.133.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.134.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.134.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.134.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.135.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.135.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.135.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.136.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.136.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.136.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.137.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.137.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.137.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.138.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.138.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.138.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.139.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.139.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.139.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.14.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.14.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.14.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.140.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.140.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.140.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.141.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.141.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.141.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.142.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.142.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.142.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.143.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.143.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.143.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.144.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.144.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.144.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.145.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.145.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.145.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.146.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.146.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.146.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.147.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.147.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.147.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.148.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.148.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.148.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.149.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.149.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.149.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.15.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.15.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.15.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.150.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.150.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.150.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.151.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.151.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.151.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.152.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.152.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.152.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.153.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.153.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.153.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.154.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.154.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.154.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.155.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.155.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.155.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.156.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.156.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.156.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.157.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.157.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.157.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.158.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.158.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.158.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.159.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.159.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.159.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.16.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.16.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.16.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.17.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.17.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.17.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.18.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.18.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.18.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.19.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.19.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.19.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.2.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.2.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.2.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.20.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.20.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.20.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.21.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.21.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.21.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.22.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.22.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.22.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.23.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.23.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.23.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.24.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.24.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.24.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.25.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.25.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.25.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.26.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.26.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.26.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.27.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.27.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.27.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.28.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.28.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.28.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.29.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.29.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.29.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.3.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.3.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.3.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.30.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.30.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.30.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.31.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.31.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.31.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.32.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.32.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.32.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.33.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.33.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.33.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.34.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.34.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.34.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.35.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.35.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.35.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.36.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.36.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.36.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.37.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.37.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.37.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.38.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.38.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.38.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.39.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.39.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.39.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.4.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.4.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.4.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.40.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.40.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.40.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.41.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.41.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.41.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.42.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.42.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.42.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.43.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.43.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.43.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.44.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.44.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.44.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.45.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.45.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.45.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.46.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.46.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.46.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.47.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.47.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.47.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.48.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.48.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.48.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.49.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.49.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.49.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.5.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.5.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.5.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.50.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.50.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.50.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.51.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.51.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.51.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.52.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.52.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.52.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.53.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.53.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.53.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.54.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.54.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.54.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.55.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.55.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.55.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.56.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.56.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.56.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.57.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.57.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.57.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.58.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.58.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.58.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.59.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.59.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.59.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.6.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.6.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.6.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.60.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.60.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.60.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.61.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.61.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.61.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.62.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.62.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.62.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.63.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.63.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.63.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.64.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.64.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.64.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.65.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.65.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.65.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.66.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.66.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.66.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.67.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.67.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.67.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.68.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.68.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.68.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.69.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.69.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.69.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.7.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.7.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.7.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.70.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.70.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.70.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.71.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.71.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.71.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.72.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.72.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.72.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.73.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.73.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.73.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.74.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.74.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.74.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.75.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.75.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.75.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.76.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.76.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.76.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.77.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.77.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.77.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.78.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.78.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.78.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.79.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.79.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.79.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.8.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.8.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.8.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.80.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.80.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.80.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.81.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.81.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.81.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.82.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.82.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.82.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.83.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.83.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.83.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.84.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.84.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.84.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.85.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.85.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.85.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.86.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.86.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.86.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.87.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.87.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.87.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.88.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.88.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.88.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.89.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.89.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.89.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.9.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.9.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.9.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.90.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.90.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.90.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.91.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.91.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.91.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.92.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.92.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.92.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.93.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.93.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.93.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.94.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.94.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.94.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.95.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.95.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.95.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.96.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.96.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.96.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.97.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.97.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.97.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.98.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.98.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.98.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.99.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.99.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.experts.99.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.gate.e_score_correction_bias": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.gate.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.k_norm.weight": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.k_proj.bias": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.q_norm.weight": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.q_proj.bias": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.v_proj.bias": "model-00086-of-00093.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00086-of-00093.safetensors", + "model.layers.86.input_layernorm.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.0.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.0.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.0.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.1.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.1.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.1.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.10.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.10.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.10.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.100.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.100.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.100.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.101.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.101.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.101.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.102.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.102.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.102.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.103.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.103.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.103.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.104.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.104.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.104.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.105.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.105.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.105.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.106.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.106.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.106.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.107.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.107.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.107.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.108.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.108.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.108.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.109.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.109.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.109.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.11.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.11.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.11.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.110.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.110.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.110.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.111.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.111.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.111.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.112.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.112.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.112.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.113.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.113.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.113.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.114.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.114.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.114.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.115.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.115.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.115.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.116.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.116.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.116.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.117.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.117.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.117.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.118.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.118.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.118.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.119.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.119.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.119.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.12.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.12.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.12.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.120.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.120.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.120.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.121.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.121.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.121.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.122.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.122.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.122.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.123.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.123.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.123.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.124.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.124.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.124.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.125.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.125.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.125.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.126.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.126.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.126.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.127.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.127.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.127.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.128.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.128.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.128.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.129.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.129.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.129.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.13.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.13.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.13.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.130.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.130.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.130.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.131.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.131.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.131.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.132.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.132.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.132.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.133.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.133.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.133.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.134.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.134.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.134.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.135.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.135.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.135.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.136.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.136.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.136.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.137.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.137.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.137.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.138.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.138.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.138.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.139.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.139.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.139.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.14.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.14.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.14.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.140.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.140.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.140.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.141.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.141.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.141.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.142.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.142.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.142.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.143.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.143.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.143.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.144.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.144.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.144.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.145.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.145.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.145.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.146.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.146.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.146.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.147.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.147.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.147.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.148.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.148.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.148.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.149.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.149.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.149.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.15.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.15.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.15.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.150.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.150.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.150.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.151.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.151.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.151.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.152.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.152.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.152.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.153.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.153.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.153.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.154.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.154.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.154.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.155.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.155.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.155.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.156.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.156.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.156.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.157.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.157.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.157.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.158.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.158.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.158.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.159.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.159.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.159.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.16.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.16.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.16.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.17.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.17.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.17.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.18.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.18.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.18.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.19.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.19.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.19.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.2.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.2.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.2.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.20.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.20.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.20.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.21.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.21.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.21.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.22.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.22.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.22.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.23.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.23.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.23.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.24.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.24.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.24.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.25.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.25.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.25.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.26.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.26.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.26.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.27.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.27.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.27.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.28.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.28.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.28.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.29.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.29.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.29.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.3.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.3.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.3.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.30.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.30.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.30.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.31.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.31.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.31.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.32.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.32.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.32.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.33.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.33.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.33.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.34.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.34.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.34.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.35.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.35.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.35.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.36.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.36.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.36.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.37.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.37.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.37.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.38.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.38.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.38.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.39.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.39.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.39.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.4.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.4.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.4.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.40.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.40.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.40.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.41.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.41.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.41.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.42.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.42.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.42.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.43.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.43.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.43.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.44.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.44.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.44.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.45.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.45.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.45.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.46.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.46.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.46.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.47.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.47.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.47.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.48.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.48.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.48.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.49.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.49.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.49.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.5.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.5.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.5.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.50.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.50.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.50.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.51.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.51.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.51.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.52.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.52.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.52.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.53.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.53.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.53.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.54.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.54.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.54.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.55.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.55.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.55.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.56.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.56.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.56.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.57.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.57.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.57.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.58.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.58.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.58.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.59.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.59.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.59.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.6.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.6.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.6.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.60.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.60.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.60.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.61.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.61.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.61.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.62.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.62.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.62.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.63.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.63.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.63.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.64.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.64.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.64.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.65.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.65.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.65.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.66.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.66.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.66.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.67.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.67.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.67.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.68.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.68.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.68.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.69.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.69.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.69.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.7.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.7.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.7.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.70.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.70.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.70.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.71.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.71.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.71.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.72.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.72.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.72.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.73.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.73.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.73.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.74.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.74.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.74.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.75.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.75.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.75.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.76.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.76.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.76.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.77.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.77.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.77.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.78.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.78.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.78.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.79.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.79.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.79.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.8.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.8.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.8.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.80.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.80.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.80.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.81.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.81.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.81.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.82.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.82.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.82.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.83.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.83.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.83.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.84.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.84.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.84.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.85.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.85.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.85.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.86.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.86.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.86.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.87.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.87.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.87.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.88.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.88.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.88.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.89.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.89.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.89.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.9.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.9.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.9.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.90.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.90.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.90.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.91.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.91.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.91.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.92.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.92.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.92.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.93.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.93.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.93.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.94.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.94.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.94.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.95.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.95.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.95.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.96.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.96.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.96.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.97.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.97.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.97.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.98.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.98.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.98.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.99.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.99.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.experts.99.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.gate.e_score_correction_bias": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.gate.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.k_norm.weight": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.k_proj.bias": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.q_norm.weight": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.q_proj.bias": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.v_proj.bias": "model-00087-of-00093.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00087-of-00093.safetensors", + "model.layers.87.input_layernorm.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.0.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.0.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.0.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.1.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.1.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.1.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.10.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.10.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.10.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.100.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.100.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.100.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.101.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.101.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.101.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.102.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.102.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.102.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.103.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.103.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.103.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.104.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.104.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.104.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.105.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.105.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.105.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.106.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.106.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.106.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.107.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.107.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.107.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.108.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.108.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.108.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.109.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.109.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.109.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.11.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.11.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.11.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.110.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.110.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.110.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.111.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.111.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.111.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.112.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.112.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.112.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.113.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.113.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.113.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.114.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.114.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.114.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.115.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.115.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.115.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.116.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.116.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.116.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.117.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.117.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.117.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.118.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.118.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.118.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.119.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.119.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.119.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.12.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.12.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.12.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.120.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.120.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.120.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.121.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.121.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.121.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.122.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.122.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.122.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.123.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.123.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.123.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.124.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.124.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.124.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.125.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.125.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.125.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.126.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.126.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.126.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.127.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.127.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.127.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.128.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.128.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.128.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.129.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.129.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.129.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.13.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.13.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.13.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.130.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.130.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.130.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.131.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.131.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.131.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.132.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.132.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.132.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.133.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.133.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.133.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.134.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.134.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.134.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.135.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.135.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.135.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.136.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.136.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.136.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.137.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.137.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.137.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.138.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.138.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.138.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.139.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.139.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.139.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.14.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.14.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.14.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.140.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.140.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.140.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.141.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.141.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.141.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.142.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.142.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.142.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.143.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.143.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.143.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.144.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.144.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.144.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.145.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.145.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.145.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.146.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.146.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.146.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.147.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.147.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.147.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.148.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.148.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.148.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.149.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.149.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.149.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.15.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.15.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.15.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.150.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.150.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.150.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.151.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.151.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.151.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.152.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.152.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.152.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.153.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.153.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.153.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.154.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.154.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.154.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.155.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.155.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.155.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.156.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.156.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.156.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.157.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.157.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.157.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.158.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.158.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.158.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.159.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.159.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.159.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.16.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.16.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.16.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.17.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.17.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.17.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.18.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.18.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.18.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.19.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.19.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.19.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.2.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.2.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.2.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.20.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.20.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.20.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.21.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.21.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.21.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.22.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.22.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.22.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.23.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.23.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.23.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.24.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.24.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.24.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.25.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.25.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.25.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.26.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.26.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.26.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.27.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.27.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.27.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.28.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.28.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.28.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.29.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.29.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.29.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.3.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.3.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.3.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.30.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.30.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.30.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.31.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.31.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.31.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.32.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.32.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.32.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.33.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.33.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.33.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.34.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.34.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.34.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.35.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.35.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.35.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.36.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.36.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.36.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.37.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.37.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.37.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.38.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.38.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.38.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.39.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.39.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.39.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.4.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.4.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.4.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.40.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.40.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.40.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.41.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.41.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.41.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.42.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.42.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.42.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.43.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.43.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.43.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.44.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.44.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.44.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.45.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.45.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.45.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.46.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.46.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.46.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.47.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.47.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.47.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.48.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.48.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.48.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.49.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.49.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.49.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.5.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.5.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.5.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.50.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.50.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.50.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.51.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.51.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.51.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.52.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.52.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.52.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.53.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.53.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.53.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.54.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.54.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.54.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.55.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.55.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.55.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.56.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.56.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.56.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.57.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.57.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.57.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.58.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.58.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.58.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.59.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.59.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.59.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.6.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.6.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.6.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.60.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.60.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.60.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.61.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.61.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.61.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.62.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.62.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.62.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.63.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.63.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.63.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.64.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.64.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.64.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.65.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.65.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.65.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.66.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.66.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.66.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.67.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.67.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.67.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.68.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.68.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.68.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.69.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.69.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.69.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.7.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.7.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.7.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.70.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.70.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.70.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.71.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.71.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.71.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.72.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.72.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.72.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.73.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.73.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.73.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.74.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.74.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.74.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.75.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.75.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.75.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.76.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.76.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.76.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.77.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.77.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.77.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.78.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.78.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.78.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.79.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.79.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.79.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.8.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.8.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.8.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.80.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.80.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.80.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.81.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.81.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.81.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.82.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.82.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.82.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.83.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.83.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.83.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.84.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.84.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.84.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.85.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.85.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.85.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.86.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.86.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.86.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.87.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.87.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.87.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.88.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.88.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.88.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.89.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.89.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.89.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.9.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.9.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.9.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.90.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.90.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.90.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.91.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.91.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.91.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.92.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.92.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.92.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.93.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.93.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.93.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.94.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.94.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.94.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.95.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.95.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.95.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.96.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.96.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.96.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.97.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.97.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.97.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.98.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.98.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.98.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.99.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.99.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.experts.99.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.gate.e_score_correction_bias": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.gate.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.k_norm.weight": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.k_proj.bias": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.q_norm.weight": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.q_proj.bias": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.v_proj.bias": "model-00088-of-00093.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00088-of-00093.safetensors", + "model.layers.88.input_layernorm.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.0.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.0.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.0.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.1.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.1.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.1.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.10.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.10.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.10.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.100.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.100.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.100.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.101.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.101.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.101.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.102.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.102.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.102.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.103.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.103.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.103.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.104.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.104.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.104.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.105.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.105.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.105.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.106.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.106.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.106.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.107.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.107.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.107.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.108.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.108.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.108.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.109.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.109.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.109.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.11.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.11.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.11.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.110.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.110.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.110.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.111.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.111.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.111.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.112.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.112.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.112.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.113.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.113.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.113.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.114.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.114.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.114.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.115.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.115.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.115.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.116.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.116.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.116.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.117.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.117.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.117.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.118.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.118.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.118.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.119.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.119.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.119.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.12.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.12.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.12.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.120.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.120.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.120.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.121.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.121.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.121.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.122.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.122.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.122.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.123.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.123.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.123.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.124.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.124.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.124.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.125.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.125.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.125.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.126.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.126.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.126.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.127.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.127.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.127.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.128.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.128.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.128.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.129.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.129.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.129.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.13.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.13.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.13.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.130.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.130.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.130.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.131.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.131.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.131.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.132.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.132.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.132.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.133.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.133.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.133.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.134.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.134.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.134.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.135.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.135.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.135.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.136.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.136.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.136.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.137.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.137.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.137.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.138.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.138.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.138.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.139.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.139.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.139.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.14.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.14.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.14.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.140.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.140.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.140.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.141.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.141.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.141.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.142.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.142.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.142.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.143.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.143.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.143.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.144.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.144.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.144.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.145.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.145.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.145.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.146.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.146.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.146.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.147.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.147.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.147.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.148.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.148.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.148.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.149.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.149.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.149.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.15.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.15.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.15.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.150.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.150.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.150.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.151.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.151.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.151.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.152.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.152.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.152.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.153.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.153.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.153.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.154.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.154.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.154.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.155.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.155.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.155.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.156.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.156.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.156.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.157.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.157.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.157.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.158.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.158.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.158.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.159.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.159.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.159.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.16.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.16.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.16.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.17.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.17.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.17.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.18.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.18.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.18.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.19.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.19.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.19.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.2.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.2.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.2.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.20.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.20.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.20.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.21.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.21.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.21.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.22.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.22.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.22.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.23.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.23.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.23.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.24.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.24.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.24.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.25.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.25.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.25.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.26.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.26.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.26.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.27.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.27.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.27.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.28.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.28.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.28.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.29.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.29.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.29.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.3.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.3.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.3.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.30.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.30.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.30.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.31.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.31.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.31.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.32.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.32.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.32.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.33.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.33.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.33.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.34.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.34.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.34.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.35.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.35.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.35.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.36.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.36.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.36.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.37.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.37.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.37.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.38.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.38.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.38.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.39.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.39.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.39.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.4.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.4.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.4.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.40.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.40.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.40.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.41.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.41.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.41.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.42.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.42.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.42.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.43.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.43.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.43.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.44.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.44.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.44.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.45.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.45.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.45.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.46.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.46.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.46.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.47.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.47.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.47.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.48.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.48.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.48.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.49.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.49.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.49.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.5.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.5.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.5.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.50.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.50.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.50.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.51.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.51.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.51.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.52.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.52.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.52.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.53.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.53.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.53.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.54.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.54.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.54.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.55.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.55.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.55.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.56.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.56.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.56.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.57.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.57.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.57.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.58.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.58.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.58.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.59.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.59.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.59.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.6.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.6.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.6.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.60.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.60.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.60.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.61.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.61.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.61.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.62.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.62.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.62.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.63.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.63.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.63.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.64.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.64.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.64.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.65.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.65.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.65.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.66.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.66.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.66.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.67.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.67.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.67.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.68.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.68.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.68.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.69.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.69.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.69.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.7.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.7.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.7.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.70.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.70.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.70.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.71.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.71.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.71.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.72.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.72.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.72.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.73.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.73.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.73.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.74.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.74.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.74.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.75.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.75.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.75.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.76.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.76.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.76.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.77.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.77.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.77.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.78.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.78.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.78.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.79.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.79.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.79.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.8.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.8.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.8.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.80.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.80.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.80.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.81.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.81.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.81.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.82.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.82.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.82.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.83.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.83.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.83.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.84.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.84.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.84.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.85.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.85.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.85.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.86.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.86.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.86.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.87.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.87.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.87.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.88.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.88.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.88.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.89.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.89.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.89.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.9.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.9.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.9.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.90.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.90.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.90.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.91.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.91.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.91.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.92.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.92.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.92.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.93.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.93.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.93.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.94.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.94.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.94.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.95.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.95.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.95.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.96.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.96.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.96.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.97.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.97.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.97.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.98.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.98.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.98.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.99.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.99.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.experts.99.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.gate.e_score_correction_bias": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.gate.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.k_norm.weight": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.k_proj.bias": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.q_norm.weight": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.q_proj.bias": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.v_proj.bias": "model-00089-of-00093.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00089-of-00093.safetensors", + "model.layers.89.input_layernorm.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.0.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.0.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.0.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.1.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.1.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.1.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.10.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.10.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.10.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.100.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.100.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.100.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.101.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.101.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.101.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.102.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.102.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.102.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.103.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.103.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.103.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.104.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.104.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.104.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.105.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.105.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.105.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.106.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.106.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.106.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.107.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.107.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.107.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.108.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.108.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.108.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.109.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.109.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.109.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.11.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.11.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.11.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.110.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.110.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.110.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.111.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.111.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.111.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.112.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.112.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.112.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.113.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.113.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.113.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.114.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.114.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.114.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.115.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.115.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.115.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.116.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.116.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.116.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.117.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.117.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.117.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.118.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.118.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.118.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.119.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.119.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.119.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.12.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.12.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.12.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.120.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.120.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.120.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.121.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.121.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.121.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.122.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.122.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.122.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.123.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.123.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.123.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.124.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.124.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.124.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.125.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.125.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.125.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.126.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.126.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.126.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.127.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.127.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.127.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.128.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.128.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.128.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.129.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.129.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.129.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.13.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.13.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.13.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.130.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.130.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.130.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.131.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.131.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.131.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.132.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.132.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.132.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.133.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.133.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.133.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.134.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.134.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.134.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.135.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.135.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.135.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.136.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.136.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.136.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.137.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.137.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.137.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.138.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.138.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.138.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.139.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.139.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.139.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.14.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.14.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.14.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.140.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.140.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.140.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.141.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.141.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.141.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.142.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.142.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.142.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.143.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.143.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.143.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.144.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.144.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.144.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.145.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.145.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.145.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.146.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.146.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.146.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.147.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.147.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.147.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.148.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.148.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.148.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.149.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.149.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.149.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.15.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.15.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.15.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.150.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.150.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.150.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.151.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.151.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.151.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.152.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.152.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.152.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.153.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.153.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.153.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.154.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.154.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.154.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.155.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.155.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.155.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.156.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.156.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.156.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.157.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.157.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.157.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.158.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.158.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.158.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.159.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.159.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.159.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.16.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.16.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.16.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.17.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.17.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.17.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.18.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.18.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.18.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.19.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.19.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.19.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.2.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.2.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.2.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.20.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.20.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.20.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.21.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.21.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.21.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.22.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.22.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.22.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.23.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.23.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.23.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.24.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.24.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.24.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.25.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.25.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.25.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.26.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.26.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.26.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.27.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.27.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.27.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.28.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.28.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.28.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.29.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.29.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.29.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.3.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.3.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.3.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.30.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.30.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.30.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.31.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.31.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.31.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.32.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.32.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.32.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.33.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.33.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.33.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.34.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.34.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.34.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.35.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.35.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.35.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.36.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.36.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.36.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.37.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.37.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.37.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.38.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.38.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.38.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.39.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.39.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.39.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.4.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.4.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.4.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.40.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.40.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.40.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.41.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.41.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.41.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.42.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.42.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.42.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.43.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.43.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.43.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.44.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.44.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.44.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.45.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.45.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.45.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.46.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.46.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.46.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.47.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.47.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.47.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.48.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.48.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.48.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.49.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.49.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.49.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.5.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.5.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.5.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.50.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.50.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.50.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.51.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.51.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.51.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.52.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.52.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.52.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.53.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.53.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.53.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.54.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.54.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.54.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.55.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.55.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.55.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.56.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.56.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.56.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.57.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.57.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.57.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.58.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.58.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.58.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.59.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.59.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.59.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.6.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.6.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.6.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.60.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.60.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.60.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.61.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.61.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.61.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.62.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.62.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.62.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.63.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.63.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.63.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.64.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.64.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.64.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.65.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.65.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.65.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.66.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.66.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.66.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.67.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.67.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.67.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.68.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.68.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.68.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.69.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.69.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.69.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.7.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.7.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.7.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.70.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.70.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.70.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.71.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.71.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.71.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.72.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.72.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.72.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.73.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.73.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.73.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.74.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.74.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.74.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.75.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.75.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.75.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.76.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.76.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.76.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.77.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.77.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.77.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.78.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.78.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.78.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.79.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.79.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.79.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.8.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.8.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.8.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.80.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.80.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.80.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.81.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.81.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.81.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.82.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.82.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.82.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.83.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.83.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.83.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.84.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.84.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.84.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.85.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.85.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.85.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.86.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.86.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.86.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.87.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.87.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.87.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.88.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.88.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.88.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.89.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.89.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.89.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.9.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.9.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.9.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.90.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.90.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.90.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.91.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.91.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.91.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.92.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.92.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.92.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.93.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.93.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.93.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.94.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.94.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.94.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.95.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.95.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.95.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.96.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.96.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.96.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.97.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.97.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.97.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.98.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.98.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.98.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.99.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.99.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.experts.99.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.gate.e_score_correction_bias": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.gate.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.k_norm.weight": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.k_proj.bias": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.q_norm.weight": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.q_proj.bias": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.v_proj.bias": "model-00090-of-00093.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00090-of-00093.safetensors", + "model.layers.90.input_layernorm.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.0.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.0.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.0.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.1.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.1.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.1.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.10.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.10.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.10.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.100.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.100.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.100.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.101.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.101.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.101.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.102.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.102.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.102.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.103.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.103.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.103.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.104.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.104.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.104.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.105.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.105.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.105.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.106.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.106.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.106.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.107.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.107.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.107.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.108.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.108.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.108.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.109.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.109.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.109.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.11.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.11.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.11.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.110.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.110.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.110.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.111.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.111.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.111.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.112.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.112.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.112.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.113.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.113.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.113.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.114.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.114.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.114.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.115.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.115.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.115.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.116.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.116.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.116.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.117.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.117.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.117.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.118.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.118.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.118.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.119.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.119.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.119.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.12.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.12.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.12.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.120.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.120.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.120.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.121.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.121.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.121.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.122.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.122.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.122.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.123.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.123.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.123.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.124.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.124.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.124.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.125.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.125.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.125.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.126.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.126.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.126.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.127.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.127.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.127.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.128.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.128.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.128.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.129.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.129.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.129.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.13.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.13.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.13.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.130.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.130.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.130.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.131.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.131.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.131.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.132.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.132.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.132.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.133.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.133.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.133.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.134.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.134.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.134.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.135.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.135.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.135.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.136.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.136.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.136.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.137.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.137.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.137.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.138.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.138.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.138.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.139.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.139.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.139.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.14.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.14.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.14.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.140.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.140.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.140.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.141.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.141.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.141.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.142.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.142.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.142.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.143.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.143.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.143.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.144.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.144.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.144.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.145.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.145.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.145.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.146.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.146.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.146.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.147.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.147.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.147.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.148.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.148.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.148.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.149.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.149.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.149.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.15.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.15.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.15.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.150.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.150.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.150.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.151.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.151.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.151.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.152.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.152.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.152.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.153.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.153.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.153.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.154.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.154.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.154.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.155.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.155.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.155.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.156.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.156.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.156.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.157.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.157.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.157.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.158.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.158.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.158.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.159.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.159.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.159.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.16.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.16.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.16.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.17.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.17.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.17.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.18.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.18.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.18.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.19.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.19.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.19.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.2.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.2.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.2.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.20.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.20.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.20.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.21.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.21.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.21.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.22.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.22.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.22.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.23.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.23.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.23.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.24.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.24.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.24.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.25.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.25.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.25.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.26.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.26.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.26.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.27.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.27.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.27.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.28.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.28.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.28.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.29.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.29.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.29.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.3.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.3.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.3.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.30.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.30.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.30.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.31.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.31.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.31.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.32.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.32.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.32.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.33.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.33.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.33.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.34.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.34.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.34.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.35.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.35.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.35.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.36.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.36.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.36.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.37.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.37.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.37.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.38.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.38.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.38.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.39.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.39.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.39.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.4.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.4.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.4.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.40.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.40.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.40.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.41.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.41.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.41.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.42.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.42.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.42.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.43.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.43.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.43.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.44.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.44.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.44.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.45.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.45.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.45.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.46.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.46.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.46.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.47.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.47.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.47.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.48.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.48.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.48.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.49.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.49.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.49.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.5.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.5.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.5.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.50.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.50.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.50.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.51.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.51.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.51.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.52.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.52.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.52.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.53.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.53.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.53.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.54.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.54.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.54.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.55.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.55.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.55.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.56.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.56.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.56.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.57.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.57.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.57.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.58.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.58.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.58.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.59.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.59.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.59.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.6.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.6.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.6.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.60.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.60.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.60.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.61.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.61.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.61.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.62.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.62.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.62.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.63.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.63.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.63.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.64.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.64.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.64.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.65.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.65.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.65.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.66.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.66.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.66.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.67.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.67.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.67.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.68.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.68.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.68.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.69.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.69.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.69.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.7.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.7.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.7.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.70.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.70.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.70.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.71.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.71.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.71.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.72.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.72.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.72.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.73.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.73.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.73.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.74.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.74.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.74.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.75.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.75.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.75.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.76.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.76.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.76.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.77.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.77.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.77.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.78.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.78.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.78.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.79.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.79.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.79.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.8.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.8.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.8.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.80.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.80.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.80.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.81.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.81.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.81.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.82.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.82.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.82.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.83.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.83.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.83.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.84.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.84.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.84.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.85.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.85.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.85.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.86.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.86.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.86.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.87.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.87.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.87.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.88.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.88.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.88.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.89.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.89.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.89.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.9.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.9.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.9.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.90.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.90.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.90.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.91.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.91.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.91.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.92.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.92.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.92.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.93.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.93.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.93.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.94.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.94.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.94.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.95.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.95.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.95.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.96.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.96.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.96.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.97.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.97.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.97.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.98.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.98.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.98.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.99.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.99.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.experts.99.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.gate.e_score_correction_bias": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.gate.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.k_norm.weight": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.k_proj.bias": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.q_norm.weight": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.q_proj.bias": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.v_proj.bias": "model-00091-of-00093.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00091-of-00093.safetensors", + "lm_head.weight": "model-00092-of-00093.safetensors", + "model.layers.91.input_layernorm.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.0.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.0.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.0.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.1.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.1.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.1.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.10.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.10.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.10.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.100.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.100.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.100.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.101.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.101.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.101.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.102.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.102.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.102.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.103.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.103.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.103.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.104.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.104.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.104.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.105.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.105.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.105.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.106.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.106.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.106.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.107.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.107.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.107.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.108.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.108.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.108.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.109.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.109.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.109.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.11.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.11.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.11.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.110.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.110.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.110.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.111.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.111.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.111.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.112.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.112.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.112.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.113.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.113.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.113.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.114.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.114.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.114.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.115.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.115.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.115.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.116.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.116.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.116.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.117.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.117.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.117.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.118.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.118.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.118.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.119.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.119.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.119.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.12.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.12.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.12.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.120.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.120.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.120.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.121.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.121.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.121.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.122.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.122.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.122.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.123.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.123.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.123.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.124.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.124.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.124.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.125.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.125.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.125.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.126.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.126.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.126.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.127.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.127.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.127.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.128.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.128.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.128.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.129.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.129.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.129.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.13.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.13.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.13.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.130.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.130.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.130.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.131.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.131.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.131.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.132.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.132.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.132.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.133.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.133.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.133.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.134.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.134.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.134.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.135.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.135.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.135.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.136.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.136.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.136.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.137.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.137.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.137.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.138.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.138.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.138.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.139.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.139.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.139.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.14.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.14.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.14.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.140.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.140.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.140.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.141.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.141.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.141.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.142.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.142.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.142.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.143.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.143.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.143.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.144.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.144.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.144.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.145.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.145.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.145.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.146.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.146.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.146.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.147.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.147.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.147.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.148.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.148.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.148.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.149.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.149.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.149.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.15.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.15.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.15.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.150.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.150.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.150.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.151.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.151.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.151.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.152.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.152.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.152.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.153.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.153.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.153.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.154.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.154.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.154.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.155.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.155.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.155.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.156.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.156.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.156.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.157.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.157.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.157.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.158.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.158.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.158.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.159.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.159.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.159.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.16.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.16.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.16.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.17.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.17.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.17.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.18.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.18.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.18.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.19.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.19.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.19.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.2.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.2.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.2.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.20.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.20.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.20.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.21.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.21.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.21.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.22.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.22.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.22.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.23.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.23.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.23.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.24.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.24.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.24.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.25.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.25.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.25.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.26.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.26.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.26.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.27.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.27.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.27.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.28.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.28.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.28.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.29.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.29.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.29.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.3.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.3.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.3.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.30.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.30.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.30.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.31.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.31.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.31.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.32.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.32.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.32.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.33.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.33.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.33.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.34.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.34.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.34.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.35.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.35.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.35.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.36.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.36.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.36.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.37.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.37.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.37.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.38.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.38.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.38.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.39.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.39.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.39.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.4.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.4.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.4.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.40.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.40.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.40.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.41.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.41.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.41.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.42.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.42.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.42.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.43.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.43.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.43.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.44.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.44.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.44.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.45.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.45.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.45.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.46.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.46.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.46.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.47.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.47.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.47.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.48.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.48.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.48.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.49.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.49.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.49.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.5.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.5.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.5.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.50.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.50.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.50.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.51.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.51.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.51.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.52.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.52.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.52.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.53.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.53.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.53.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.54.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.54.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.54.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.55.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.55.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.55.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.56.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.56.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.56.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.57.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.57.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.57.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.58.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.58.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.58.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.59.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.59.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.59.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.6.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.6.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.6.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.60.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.60.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.60.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.61.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.61.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.61.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.62.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.62.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.62.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.63.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.63.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.63.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.64.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.64.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.64.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.65.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.65.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.65.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.66.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.66.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.66.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.67.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.67.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.67.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.68.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.68.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.68.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.69.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.69.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.69.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.7.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.7.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.7.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.70.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.70.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.70.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.71.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.71.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.71.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.72.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.72.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.72.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.73.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.73.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.73.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.74.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.74.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.74.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.75.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.75.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.75.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.76.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.76.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.76.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.77.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.77.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.77.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.78.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.78.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.78.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.79.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.79.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.79.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.8.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.8.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.8.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.80.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.80.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.80.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.81.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.81.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.81.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.82.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.82.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.82.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.83.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.83.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.83.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.84.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.84.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.84.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.85.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.85.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.85.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.86.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.86.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.86.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.87.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.87.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.87.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.88.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.88.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.88.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.89.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.89.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.89.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.9.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.9.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.9.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.90.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.90.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.90.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.91.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.91.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.91.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.92.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.92.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.92.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.93.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.93.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.93.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.94.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.94.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.94.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.95.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.95.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.95.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.96.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.96.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.96.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.97.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.97.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.97.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.98.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.98.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.98.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.99.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.99.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.experts.99.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.gate.e_score_correction_bias": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.gate.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.k_norm.weight": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.k_proj.bias": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.q_norm.weight": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.q_proj.bias": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.v_proj.bias": "model-00092-of-00093.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00092-of-00093.safetensors", + "model.layers.92.shared_head.head.weight": "model-00092-of-00093.safetensors", + "model.norm.weight": "model-00092-of-00093.safetensors", + "model.layers.92.eh_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.enorm.weight": "model-00093-of-00093.safetensors", + "model.layers.92.hnorm.weight": "model-00093-of-00093.safetensors", + "model.layers.92.input_layernorm.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.0.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.0.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.0.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.1.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.1.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.1.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.10.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.10.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.10.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.100.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.100.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.100.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.101.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.101.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.101.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.102.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.102.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.102.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.103.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.103.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.103.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.104.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.104.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.104.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.105.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.105.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.105.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.106.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.106.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.106.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.107.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.107.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.107.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.108.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.108.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.108.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.109.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.109.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.109.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.11.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.11.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.11.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.110.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.110.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.110.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.111.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.111.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.111.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.112.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.112.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.112.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.113.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.113.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.113.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.114.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.114.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.114.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.115.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.115.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.115.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.116.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.116.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.116.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.117.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.117.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.117.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.118.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.118.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.118.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.119.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.119.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.119.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.12.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.12.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.12.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.120.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.120.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.120.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.121.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.121.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.121.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.122.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.122.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.122.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.123.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.123.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.123.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.124.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.124.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.124.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.125.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.125.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.125.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.126.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.126.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.126.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.127.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.127.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.127.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.128.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.128.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.128.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.129.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.129.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.129.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.13.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.13.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.13.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.130.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.130.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.130.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.131.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.131.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.131.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.132.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.132.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.132.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.133.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.133.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.133.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.134.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.134.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.134.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.135.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.135.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.135.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.136.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.136.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.136.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.137.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.137.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.137.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.138.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.138.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.138.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.139.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.139.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.139.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.14.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.14.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.14.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.140.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.140.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.140.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.141.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.141.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.141.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.142.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.142.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.142.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.143.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.143.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.143.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.144.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.144.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.144.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.145.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.145.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.145.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.146.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.146.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.146.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.147.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.147.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.147.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.148.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.148.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.148.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.149.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.149.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.149.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.15.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.15.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.15.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.150.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.150.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.150.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.151.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.151.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.151.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.152.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.152.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.152.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.153.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.153.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.153.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.154.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.154.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.154.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.155.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.155.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.155.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.156.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.156.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.156.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.157.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.157.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.157.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.158.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.158.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.158.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.159.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.159.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.159.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.16.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.16.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.16.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.17.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.17.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.17.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.18.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.18.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.18.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.19.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.19.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.19.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.2.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.2.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.2.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.20.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.20.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.20.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.21.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.21.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.21.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.22.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.22.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.22.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.23.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.23.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.23.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.24.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.24.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.24.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.25.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.25.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.25.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.26.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.26.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.26.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.27.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.27.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.27.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.28.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.28.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.28.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.29.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.29.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.29.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.3.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.3.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.3.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.30.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.30.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.30.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.31.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.31.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.31.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.32.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.32.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.32.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.33.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.33.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.33.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.34.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.34.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.34.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.35.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.35.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.35.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.36.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.36.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.36.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.37.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.37.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.37.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.38.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.38.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.38.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.39.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.39.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.39.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.4.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.4.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.4.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.40.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.40.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.40.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.41.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.41.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.41.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.42.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.42.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.42.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.43.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.43.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.43.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.44.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.44.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.44.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.45.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.45.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.45.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.46.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.46.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.46.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.47.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.47.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.47.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.48.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.48.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.48.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.49.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.49.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.49.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.5.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.5.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.5.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.50.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.50.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.50.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.51.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.51.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.51.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.52.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.52.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.52.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.53.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.53.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.53.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.54.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.54.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.54.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.55.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.55.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.55.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.56.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.56.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.56.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.57.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.57.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.57.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.58.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.58.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.58.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.59.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.59.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.59.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.6.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.6.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.6.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.60.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.60.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.60.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.61.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.61.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.61.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.62.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.62.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.62.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.63.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.63.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.63.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.64.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.64.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.64.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.65.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.65.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.65.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.66.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.66.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.66.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.67.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.67.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.67.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.68.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.68.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.68.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.69.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.69.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.69.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.7.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.7.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.7.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.70.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.70.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.70.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.71.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.71.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.71.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.72.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.72.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.72.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.73.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.73.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.73.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.74.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.74.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.74.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.75.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.75.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.75.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.76.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.76.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.76.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.77.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.77.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.77.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.78.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.78.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.78.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.79.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.79.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.79.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.8.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.8.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.8.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.80.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.80.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.80.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.81.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.81.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.81.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.82.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.82.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.82.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.83.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.83.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.83.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.84.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.84.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.84.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.85.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.85.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.85.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.86.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.86.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.86.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.87.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.87.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.87.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.88.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.88.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.88.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.89.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.89.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.89.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.9.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.9.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.9.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.90.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.90.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.90.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.91.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.91.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.91.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.92.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.92.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.92.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.93.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.93.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.93.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.94.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.94.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.94.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.95.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.95.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.95.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.96.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.96.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.96.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.97.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.97.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.97.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.98.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.98.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.98.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.99.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.99.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.experts.99.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.gate.e_score_correction_bias": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.gate.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.shared_experts.down_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.shared_experts.gate_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.mlp.shared_experts.up_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.post_attention_layernorm.weight": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.k_norm.weight": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.k_proj.bias": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.k_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.o_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.q_norm.weight": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.q_proj.bias": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.q_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.v_proj.bias": "model-00093-of-00093.safetensors", + "model.layers.92.self_attn.v_proj.weight": "model-00093-of-00093.safetensors", + "model.layers.92.shared_head.norm.weight": "model-00093-of-00093.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..4df37ba53ea68ab791aff73d452ec032d46b68be --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,40 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ed3c66baf1ec4de61840b0abf02142687bfed8 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba +size 19970700 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b95552c433cc26db3af37c15a23fae43231222b3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,328 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "[MASK]", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": null, + "chat_template": "[gMASK]\n{%- if tools -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n\n{% for tool in tools %}\n{{ tool | tojson|string }}\n{% endfor %}\n\n\nFor each function call, output the function name and arguments within the following XML format:\n{function-name}\n{arg-key-1}\n{arg-value-1}\n{arg-key-2}\n{arg-value-2}\n...\n{%- endif -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {% set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{% for m in messages %}\n{%- if m.role == 'user' -%}<|user|>\n{{ visible_text(m.content) }}\n{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith(\"/nothink\")) else '' -}}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set reasoning_content = '' %}\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = ((content.split('')|first).rstrip('\\n').split('')|last).lstrip('\\n') %}\n {%- set content = (content.split('')|last).lstrip('\\n') %}\n {%- endif %}\n{%- endif %}\n{%- if loop.index0 > ns.last_user_index and reasoning_content -%}\n{{ '\\n' + reasoning_content.strip() + ''}}\n{%- else -%}\n{{ '\\n' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ '\\n' + content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{ '\\n' + tc.name }}\n{% set _args = tc.arguments %}\n{% for k, v in _args.items() %}\n{{ k }}\n{{ v | tojson|string if v is not string else v }}\n{% endfor %}\n{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if m.content is string -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' }}\n{%- endif %}\n{{- '\\n\\n' }}\n{{- m.content }}\n{{- '\\n' }}\n{%- else -%}\n<|observation|>{% for tr in m.content %}\n\n\n{{ tr.output if tr.output is defined else tr }}\n{% endfor -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>\n{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '\\n' if (enable_thinking is defined and not enable_thinking) else '' -}}\n{%- endif -%}" +} \ No newline at end of file