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/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..15633276a7c317d4619c7d9283ec3286492e3f8b --- /dev/null +++ b/README.md @@ -0,0 +1,54 @@ +--- +language: +- en +license: llama3 +tags: +- Llama-3.1 +- instruct +- finetune +- reasoning +- hybrid-mode +- chatml +- function calling +- tool use +- json mode +- structured outputs +- atropos +- dataforge +- long context +- roleplaying +- chat +- mlx +base_model: NousResearch/Hermes-4-405B +library_name: transformers +widget: +- example_title: Hermes 4 + messages: + - role: system + content: You are Hermes 4, a capable, neutrally-aligned assistant. Prefer concise, + correct answers. + - role: user + content: Explain the difference between BFS and DFS to a new CS student. +model-index: +- name: Hermes-4-Llama-3.1-405B + results: [] +--- +## 💫 Community Model> Hermes-4-405B by NousResearch + +_👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)_. + +**Model creator**: [NousResearch](https://huggingface.co/NousResearch)
+**Original model**: [Hermes-4-405B](https://huggingface.co/NousResearch/Hermes-4-405B)
+**MLX quantization**: provided by [LM Studio team](https://x.com/lmstudio) using [mlx_lm](https://github.com/ml-explore/mlx-lm)
+ +## Technical Details + +6-bit quantized version of Hermes-4-405B using MLX, optimized for Apple Silicon. + +## Special thanks + +🙏 Special thanks to the [Apple Machine Learning Research](https://github.com/ml-explore) team for creating [MLX](https://github.com/ml-explore/mlx). + +## Disclaimers + +LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..d894f3b5ebdfe9e094f56e79259fe779156ca47a --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,76 @@ +{%- set thinking_prompt = 'You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside tags, and then provide your solution or response to the problem.' %} +{%- set standard_prompt = 'You are Hermes, created by Nous Research.' %} +{%- if not thinking is defined %}{% set thinking = false %}{% endif %} +{%- if not keep_cots is defined %}{% set keep_cots = false %}{% endif %} +{%- if thinking %}{%- set system_prompt = thinking_prompt %}{%- else %}{%- set system_prompt = standard_prompt %}{%- endif %} +{%- if tools %} + {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- system_prompt }} + {%- endif %} + {{- "\n\n# Tools\n\nYou are a function calling AI model. You may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": \"\", \"arguments\": }\n<|eot_id|>" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + messages[0]['content'] + '<|eot_id|>' }} + {%- else %} + {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + system_prompt + '<|eot_id|>' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n\n' + message.content + '<|eot_id|>' }} + {%- elif (message.role == "assistant" and not message.tool_calls) %} + {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }} + {%- if message.content %} + {%- set content = message['content'] -%} + {%- if thinking %} + {%- if not keep_cots %} + {%- set content = ' ' + content.split('', 1)[1] -%} + {%- endif %} + {%- endif %} + {{- '\n' + content + '<|eot_id|>' }} + {%- endif %} + {%- elif message.role == "assistant" %} + {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }} + {%- if message.content %} + {%- set content = message['content'] -%} + {%- if thinking %} + {%- if not keep_cots %} + {%- set content = ' ' + content.split('', 1)[1] -%} + {%- endif %} + {%- endif %} + {{- '\n' + content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|eot_id|>' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|start_header_id|>user<|end_header_id|>\n' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|eot_id|>' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47b66cb93df0c5ea3cf2ebf76c44533ce7d9c443 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 16384, + "initializer_range": 0.02, + "intermediate_size": 53248, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 128, + "num_hidden_layers": 126, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "quantization": { + "group_size": 64, + "bits": 6 + }, + "quantization_config": { + "group_size": 64, + "bits": 6 + }, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.52.4", + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..27a9e4c5a8b7c8e0394f0e31149ae19d4822dcd3 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.52.4" +} diff --git a/model-00001-of-00064.safetensors b/model-00001-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53e38d188465942e20182f3ac4c596b3ce021c57 --- /dev/null +++ b/model-00001-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45175dd79a49a11b346232d7cb8bd91d276c23065315061eb2c8c69621287f55 +size 4760867066 diff --git a/model-00007-of-00064.safetensors b/model-00007-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..107119e337065081b8819df99f0c76f1ebb0cbc5 --- /dev/null +++ b/model-00007-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950c0283879820a19e2d8be07b89132bb57a1a17e80f6c6d2a9c5ffad2f79a7e +size 5180101854 diff --git a/model-00010-of-00064.safetensors b/model-00010-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c970d03d960b1053c14ab66cb0ea4be908322668 --- /dev/null +++ b/model-00010-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a70c2af32c00ea05dbe5d8e0d36626966aded63f7e051f670668848fdd6df45f +size 5180101868 diff --git a/model-00011-of-00064.safetensors b/model-00011-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36ad75c28506c3431dad4c3006b06be2e7201446 --- /dev/null +++ b/model-00011-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1bc5e255141a0932fda981071729862d375e5585a5b442caaa9ed76546dbbf +size 5180101858 diff --git a/model-00013-of-00064.safetensors b/model-00013-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ecc3fcdabfd0461e3f6fe35917eeb4d0527556e --- /dev/null +++ b/model-00013-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a1e643c9d5cb45c3125859a08be10d3eaae5040fbd7be8be6cc1c59a16f747 +size 5180101844 diff --git a/model-00014-of-00064.safetensors b/model-00014-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9069017b6e02e68113e431a38ad92a7356cf44b4 --- /dev/null +++ b/model-00014-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e41976057a3b176617f66a28633be23d3bb0f320d827180a123e1d61803daf +size 5180101850 diff --git a/model-00015-of-00064.safetensors b/model-00015-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74993b44bc4414536cdc05bc2691a21fddf07f68 --- /dev/null +++ b/model-00015-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0e831db5ece81c277df8c04188b4f7900cbfcb114359e2249f375c606932158 +size 5180101850 diff --git a/model-00017-of-00064.safetensors b/model-00017-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3a0a9518484ed6012898f3f88f1fdce24a5d27f --- /dev/null +++ b/model-00017-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb093219cb46875842ef142270f5eac22d92f61dd1e99ea0e8de96b5df6eb02b +size 5180101866 diff --git a/model-00018-of-00064.safetensors b/model-00018-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dde0eeb9a8c926f3b2ed80e533ea76ae75e6abfc --- /dev/null +++ b/model-00018-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a14bb3c5c6330ec169d6076bfa7b4242df593bc4525f91a6cdf007efa4dae2 +size 5180101852 diff --git a/model-00019-of-00064.safetensors b/model-00019-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..75bdf0d8a596393ba67050859bd0920664a8f75a --- /dev/null +++ b/model-00019-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e7c5c19b16512e35de3a25463c221e078a2e1ab45c857cdf384a863224cab5 +size 5180101850 diff --git a/model-00023-of-00064.safetensors b/model-00023-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f4e428cc7f8ec54fe0c641acd89a5e0a6afd402 --- /dev/null +++ b/model-00023-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8c4c706dd4671c4a2270c52eedf91869dcdf55093cbc914903dad7384eabf2 +size 5180101844 diff --git a/model-00027-of-00064.safetensors b/model-00027-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c89187d1c3eb9f4ea0cb4d3aa581acef0e371545 --- /dev/null +++ b/model-00027-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6916b8af7da9482d4a55cfbd016c2a50cd52d4f097235be5837da963c4ab960 +size 5180101866 diff --git a/model-00028-of-00064.safetensors b/model-00028-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a0942b412780d82e4e303b75df28eaf7a36f967 --- /dev/null +++ b/model-00028-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ab483746a0f416a70b88d19e123f395ba516c8b625dfbec73d24d118a420fa +size 5180101848 diff --git a/model-00029-of-00064.safetensors b/model-00029-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8759d14eb0fc33fdf6c1d45c199b01ed35b35c81 --- /dev/null +++ b/model-00029-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd8320ac1d6dae47dd00552526814a6c00f953b23387bf732d508a058be102d +size 5180101862 diff --git a/model-00030-of-00064.safetensors b/model-00030-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a92936d17e1f2662c35d34ef7264e2609e8780d --- /dev/null +++ b/model-00030-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f31c8da5bf37772a4b36fb14d080b76ae4f4826548e43d418a552909c3a7656 +size 5180101862 diff --git a/model-00032-of-00064.safetensors b/model-00032-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f115bed005594b4be7ded224dd884c35bbd3615 --- /dev/null +++ b/model-00032-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:013b4a0a04059223166962c9e2af5bb208aff0a2b5fc6a6efd2d6e0d678ed8c6 +size 5180101848 diff --git a/model-00033-of-00064.safetensors b/model-00033-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24940bd5ad5a5a7e4530171f5c01fbf9f720c10a --- /dev/null +++ b/model-00033-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d50b64f860dd0300faf69c4f5677562c772dd9d1a344fd87714ff0c644b02df +size 5180101870 diff --git a/model-00035-of-00064.safetensors b/model-00035-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0c243580c9b3ca0439ec3c4430e8bc061b720a3 --- /dev/null +++ b/model-00035-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44342d296cf1cbbe345468547ee6f49251d2d92dd8b805d575f0c3fb14eb5db +size 5180101860 diff --git a/model-00037-of-00064.safetensors b/model-00037-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f40485e3b0264dcdbbaf299db73a6439dcee86c --- /dev/null +++ b/model-00037-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db61a1c281eb24fe9fb487caa07097630192d11d2a23c2af6672c5551561742d +size 5180101844 diff --git a/model-00038-of-00064.safetensors b/model-00038-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da4288a332e4b901995951c2ae0dd376d00f3b06 --- /dev/null +++ b/model-00038-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41bb8f64f8896d1967bcb6f6f6df87663a9bf73e099c9fa618623f59d701b34d +size 5180101846 diff --git a/model-00039-of-00064.safetensors b/model-00039-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e4f2f381247050feec4542f11cb8af60d4839e0 --- /dev/null +++ b/model-00039-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0ff46e605f27ec44bca9b490bfc561ebcef77c720829553d49b2308496d3b5 +size 5180101852 diff --git a/model-00040-of-00064.safetensors b/model-00040-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ebb8b88091d70ced258332f5c881f01669dae8ba --- /dev/null +++ b/model-00040-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af63339cce11c5e627005e6d91a16ed49a45a909db822f97c5b4d6a488c14fe +size 5180101862 diff --git a/model-00042-of-00064.safetensors b/model-00042-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ad9f10667b83a76706bff61fdcd713d3edc598e --- /dev/null +++ b/model-00042-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d529cfed1eb9d90bcfe91a61eee9b03c6d96a514f2489eaa561e279858b10a +size 5180101820 diff --git a/model-00043-of-00064.safetensors b/model-00043-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f4b61c31ac5afe999cdcaf7580a266e7f389d166 --- /dev/null +++ b/model-00043-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9ad32a0c5172576e095a8f399025401a0919b5e8109326be45fe9b47c68c4e +size 5180101852 diff --git a/model-00045-of-00064.safetensors b/model-00045-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3308128b862da878d556d69d3ad1f954e07644dc --- /dev/null +++ b/model-00045-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c72fb459b120d2a89c973495386c5c1e2612c761b14b5e62fd443be81858f9d +size 5180101840 diff --git a/model-00046-of-00064.safetensors b/model-00046-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..facee6540597a7524ed310cea82a64b08c168024 --- /dev/null +++ b/model-00046-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc894833cc6953e9a46d77363156da89cd440276f4538c6126e215c6fa8a1a7b +size 5180101864 diff --git a/model-00048-of-00064.safetensors b/model-00048-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..121c023157795ca048755c83a542927e3b2581cc --- /dev/null +++ b/model-00048-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a742228093674ba9d6079462d2d52e2a967d4fde66c738533bc6f77468973c03 +size 5180101846 diff --git a/model-00049-of-00064.safetensors b/model-00049-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95349bffdc5e968147e818d89d439bd0dacfbe0b --- /dev/null +++ b/model-00049-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abf6f19240284f19707ad87da0c65201dc3c2746f0975063fe76431de8d5fa0 +size 5180101864 diff --git a/model-00051-of-00064.safetensors b/model-00051-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3134529e4d885c8ad028cf5c11d7a87d041447bf --- /dev/null +++ b/model-00051-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28625b2effa90ed529eca9ae9b07f0b88acaa2c684a6778777db34de8468db68 +size 5180101887 diff --git a/model-00052-of-00064.safetensors b/model-00052-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ea5c2ef3e33efa28b95f87c5abc04754eeae037 --- /dev/null +++ b/model-00052-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1d50b74f5962da4fe3c95fe629354345cd9639d89051337b86141a814b2441 +size 5180101900 diff --git a/model-00053-of-00064.safetensors b/model-00053-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f4878af61a0ae7dcf02ff24987c49add4a9ef113 --- /dev/null +++ b/model-00053-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ae731aa358a975c5bd13c2a8818cdbcbec125a7d2df975f89cc26dd0476e8e +size 5180101900 diff --git a/model-00054-of-00064.safetensors b/model-00054-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3be4b1b91845dad550cc929685b6eca9a35a727 --- /dev/null +++ b/model-00054-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79da7b84f09b258979f4d5804fc28ea54d92b87ff508249534423b38fc31b61d +size 5180101892 diff --git a/model-00055-of-00064.safetensors b/model-00055-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04a46ab9c5a48ed8144197839f78240b1f3ba59d --- /dev/null +++ b/model-00055-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4359e9f4a7626f482181f8107fdfc57bcfee418766cae597215191f38133ab5c +size 5180101918 diff --git a/model-00056-of-00064.safetensors b/model-00056-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..970b41ab68c2d5b888d419d5ea6924df644a9f79 --- /dev/null +++ b/model-00056-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa955017e607fc89e55070e3c5d728ce9b5674a367c913ebe0fc180244573650 +size 5180101898 diff --git a/model-00057-of-00064.safetensors b/model-00057-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f57011adcb32361b0d35a53363672f1cd24f76a --- /dev/null +++ b/model-00057-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:710e962c777872c35d89d0341c387f7feaa8184924bf3ee33ffec23b835acfcc +size 5180101904 diff --git a/model-00058-of-00064.safetensors b/model-00058-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c220351f18ebdc3c4389c4ba6a1f210f7519b3f --- /dev/null +++ b/model-00058-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38e13d41c2ec787ffa5b7c801a5f1b3f1347f955e82941cbf9c2169d4451eca +size 5180101920 diff --git a/model-00059-of-00064.safetensors b/model-00059-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bfbeeb801b3d089b93037bc5f3eeba8e19043f3 --- /dev/null +++ b/model-00059-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da211dc9cef404a0603e39a6e9c8e8649ceace417ee3d92bfc12236d43f7d897 +size 5180101914 diff --git a/model-00060-of-00064.safetensors b/model-00060-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a7c153b772654cd9064d5e75ffd4eb71c512079 --- /dev/null +++ b/model-00060-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3218c4d3fbdf9b431b9183d45d4159b774d36d2065a61a6b78f30da5411da747 +size 5180101924 diff --git a/model-00061-of-00064.safetensors b/model-00061-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9cf32709181bb9a2d2dfd00b04796d54d4d0f02e --- /dev/null +++ b/model-00061-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df3b325686eb354da35bbb1ac0e8c87063cbdd6ba946b45f9b63e05787f4d10 +size 5180101902 diff --git a/model-00062-of-00064.safetensors b/model-00062-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67ed90b33a105fae2c35bd02e1142fe490a04ce3 --- /dev/null +++ b/model-00062-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd266da3cb8a4a13626c9e10cc36f6c050669c883c7e9b0bd7ba6f52e51f07ec +size 5180101914 diff --git a/model-00063-of-00064.safetensors b/model-00063-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8fc77fb40f97fe96f02bb1825615627ffe047449 --- /dev/null +++ b/model-00063-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebdd1461013f0cb05de74323e2270c8a8cef6d42b12459072fef78ce6cfe8fb +size 5180101898 diff --git a/model-00064-of-00064.safetensors b/model-00064-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..556daa1306a137ff087c04562b5ec74c0fc35e0d --- /dev/null +++ b/model-00064-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ce09361abc7593205284c247d75d186b1ddc6c90d74fb3888dc2f61ba0f211 +size 3833955981 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..665cf18c9d43b8e83c39d2918b03be759405bbc7 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,2913 @@ +{ + "metadata": { + "total_size": 329760800768, + "total_parameters": 405853388800 + }, + "weight_map": { + "lm_head.biases": "model-00064-of-00064.safetensors", + "lm_head.scales": "model-00064-of-00064.safetensors", + "lm_head.weight": "model-00064-of-00064.safetensors", + "model.embed_tokens.biases": "model-00001-of-00064.safetensors", + "model.embed_tokens.scales": "model-00001-of-00064.safetensors", + "model.embed_tokens.weight": "model-00001-of-00064.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.down_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.up_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.down_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.gate_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.up_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00064.safetensors", + "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00064.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00064.safetensors", + "model.layers.10.input_layernorm.weight": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.down_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.gate_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.up_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.k_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.o_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.q_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.v_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.100.input_layernorm.weight": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.down_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.down_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.down_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.gate_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.gate_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.gate_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.up_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.up_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.100.mlp.up_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.100.post_attention_layernorm.weight": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.k_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.k_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.k_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.o_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.o_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.o_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.q_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.q_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.q_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.v_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.v_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.100.self_attn.v_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.101.input_layernorm.weight": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.down_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.down_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.down_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.gate_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.gate_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.gate_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.up_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.up_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.101.mlp.up_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.101.post_attention_layernorm.weight": "model-00052-of-00064.safetensors", + "model.layers.101.self_attn.k_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.k_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.k_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.o_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.o_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.o_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.q_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.q_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.q_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.v_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.v_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.101.self_attn.v_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.102.input_layernorm.weight": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.down_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.down_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.down_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.gate_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.gate_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.gate_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.up_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.up_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.102.mlp.up_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.102.post_attention_layernorm.weight": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.k_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.k_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.k_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.o_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.o_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.o_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.q_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.q_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.q_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.v_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.v_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.102.self_attn.v_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.103.input_layernorm.weight": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.down_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.down_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.down_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.gate_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.gate_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.gate_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.up_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.up_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.103.mlp.up_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.103.post_attention_layernorm.weight": "model-00053-of-00064.safetensors", + "model.layers.103.self_attn.k_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.k_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.k_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.o_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.o_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.o_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.q_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.q_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.q_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.v_proj.biases": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.v_proj.scales": "model-00052-of-00064.safetensors", + "model.layers.103.self_attn.v_proj.weight": "model-00052-of-00064.safetensors", + "model.layers.104.input_layernorm.weight": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.down_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.down_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.down_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.gate_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.gate_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.gate_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.up_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.up_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.104.mlp.up_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.104.post_attention_layernorm.weight": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.k_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.k_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.k_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.o_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.o_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.o_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.q_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.q_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.q_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.v_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.v_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.104.self_attn.v_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.105.input_layernorm.weight": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.down_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.down_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.down_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.gate_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.gate_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.gate_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.up_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.up_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.105.mlp.up_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.105.post_attention_layernorm.weight": "model-00054-of-00064.safetensors", + "model.layers.105.self_attn.k_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.k_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.k_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.o_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.o_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.o_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.q_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.q_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.q_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.v_proj.biases": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.v_proj.scales": "model-00053-of-00064.safetensors", + "model.layers.105.self_attn.v_proj.weight": "model-00053-of-00064.safetensors", + "model.layers.106.input_layernorm.weight": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.down_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.down_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.down_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.gate_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.gate_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.gate_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.up_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.up_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.106.mlp.up_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.106.post_attention_layernorm.weight": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.k_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.k_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.k_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.o_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.o_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.o_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.q_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.q_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.q_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.v_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.v_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.106.self_attn.v_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.107.input_layernorm.weight": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.down_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.down_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.down_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.gate_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.gate_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.gate_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.up_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.up_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.107.mlp.up_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.107.post_attention_layernorm.weight": "model-00055-of-00064.safetensors", + "model.layers.107.self_attn.k_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.k_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.k_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.o_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.o_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.o_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.q_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.q_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.q_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.v_proj.biases": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.v_proj.scales": "model-00054-of-00064.safetensors", + "model.layers.107.self_attn.v_proj.weight": "model-00054-of-00064.safetensors", + "model.layers.108.input_layernorm.weight": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.down_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.down_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.down_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.gate_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.gate_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.gate_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.up_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.up_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.108.mlp.up_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.108.post_attention_layernorm.weight": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.k_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.k_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.k_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.o_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.o_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.o_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.q_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.q_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.q_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.v_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.v_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.108.self_attn.v_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.109.input_layernorm.weight": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.down_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.down_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.down_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.gate_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.gate_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.gate_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.up_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.up_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.109.mlp.up_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.109.post_attention_layernorm.weight": "model-00056-of-00064.safetensors", + "model.layers.109.self_attn.k_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.k_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.k_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.o_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.o_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.o_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.q_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.q_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.q_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.v_proj.biases": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.v_proj.scales": "model-00055-of-00064.safetensors", + "model.layers.109.self_attn.v_proj.weight": "model-00055-of-00064.safetensors", + "model.layers.11.input_layernorm.weight": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.down_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.gate_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.up_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00064.safetensors", + "model.layers.11.self_attn.k_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.o_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.q_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.v_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.110.input_layernorm.weight": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.down_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.down_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.down_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.gate_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.gate_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.gate_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.up_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.up_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.110.mlp.up_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.110.post_attention_layernorm.weight": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.k_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.k_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.k_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.o_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.o_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.o_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.q_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.q_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.q_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.v_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.v_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.110.self_attn.v_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.111.input_layernorm.weight": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.down_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.down_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.down_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.gate_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.gate_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.gate_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.up_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.up_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.111.mlp.up_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.111.post_attention_layernorm.weight": "model-00057-of-00064.safetensors", + "model.layers.111.self_attn.k_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.k_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.k_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.o_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.o_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.o_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.q_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.q_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.q_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.v_proj.biases": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.v_proj.scales": "model-00056-of-00064.safetensors", + "model.layers.111.self_attn.v_proj.weight": "model-00056-of-00064.safetensors", + "model.layers.112.input_layernorm.weight": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.down_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.down_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.down_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.gate_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.gate_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.gate_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.up_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.up_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.112.mlp.up_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.112.post_attention_layernorm.weight": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.k_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.k_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.k_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.o_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.o_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.o_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.q_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.q_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.q_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.v_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.v_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.112.self_attn.v_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.113.input_layernorm.weight": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.down_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.down_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.down_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.gate_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.gate_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.gate_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.up_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.up_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.113.mlp.up_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.113.post_attention_layernorm.weight": "model-00058-of-00064.safetensors", + "model.layers.113.self_attn.k_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.k_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.k_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.o_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.o_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.o_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.q_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.q_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.q_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.v_proj.biases": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.v_proj.scales": "model-00057-of-00064.safetensors", + "model.layers.113.self_attn.v_proj.weight": "model-00057-of-00064.safetensors", + "model.layers.114.input_layernorm.weight": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.down_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.down_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.down_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.gate_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.gate_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.gate_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.up_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.up_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.114.mlp.up_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.114.post_attention_layernorm.weight": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.k_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.k_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.k_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.o_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.o_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.o_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.q_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.q_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.q_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.v_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.v_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.114.self_attn.v_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.115.input_layernorm.weight": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.down_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.down_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.down_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.gate_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.gate_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.gate_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.up_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.up_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.115.mlp.up_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.115.post_attention_layernorm.weight": "model-00059-of-00064.safetensors", + "model.layers.115.self_attn.k_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.k_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.k_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.o_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.o_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.o_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.q_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.q_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.q_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.v_proj.biases": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.v_proj.scales": "model-00058-of-00064.safetensors", + "model.layers.115.self_attn.v_proj.weight": "model-00058-of-00064.safetensors", + "model.layers.116.input_layernorm.weight": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.down_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.down_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.down_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.gate_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.gate_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.gate_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.up_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.up_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.116.mlp.up_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.116.post_attention_layernorm.weight": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.k_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.k_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.k_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.o_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.o_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.o_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.q_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.q_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.q_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.v_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.v_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.116.self_attn.v_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.117.input_layernorm.weight": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.down_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.down_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.down_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.gate_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.gate_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.gate_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.up_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.up_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.117.mlp.up_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.117.post_attention_layernorm.weight": "model-00060-of-00064.safetensors", + "model.layers.117.self_attn.k_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.k_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.k_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.o_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.o_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.o_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.q_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.q_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.q_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.v_proj.biases": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.v_proj.scales": "model-00059-of-00064.safetensors", + "model.layers.117.self_attn.v_proj.weight": "model-00059-of-00064.safetensors", + "model.layers.118.input_layernorm.weight": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.down_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.down_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.down_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.gate_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.gate_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.gate_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.up_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.up_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.118.mlp.up_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.118.post_attention_layernorm.weight": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.k_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.k_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.k_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.o_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.o_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.o_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.q_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.q_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.q_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.v_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.v_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.118.self_attn.v_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.119.input_layernorm.weight": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.down_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.down_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.down_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.gate_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.gate_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.gate_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.up_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.up_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.119.mlp.up_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.119.post_attention_layernorm.weight": "model-00061-of-00064.safetensors", + "model.layers.119.self_attn.k_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.k_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.k_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.o_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.o_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.o_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.q_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.q_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.q_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.v_proj.biases": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.v_proj.scales": "model-00060-of-00064.safetensors", + "model.layers.119.self_attn.v_proj.weight": "model-00060-of-00064.safetensors", + "model.layers.12.input_layernorm.weight": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.down_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.gate_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.up_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.k_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.o_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.q_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.v_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.120.input_layernorm.weight": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.down_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.down_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.down_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.gate_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.gate_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.gate_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.up_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.up_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.120.mlp.up_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.120.post_attention_layernorm.weight": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.k_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.k_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.k_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.o_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.o_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.o_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.q_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.q_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.q_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.v_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.v_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.120.self_attn.v_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.121.input_layernorm.weight": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.down_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.down_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.down_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.gate_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.gate_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.gate_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.up_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.up_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.121.mlp.up_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.121.post_attention_layernorm.weight": "model-00062-of-00064.safetensors", + "model.layers.121.self_attn.k_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.k_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.k_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.o_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.o_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.o_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.q_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.q_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.q_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.v_proj.biases": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.v_proj.scales": "model-00061-of-00064.safetensors", + "model.layers.121.self_attn.v_proj.weight": "model-00061-of-00064.safetensors", + "model.layers.122.input_layernorm.weight": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.down_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.down_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.down_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.gate_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.gate_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.gate_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.up_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.up_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.122.mlp.up_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.122.post_attention_layernorm.weight": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.k_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.k_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.k_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.o_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.o_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.o_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.q_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.q_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.q_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.v_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.v_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.122.self_attn.v_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.123.input_layernorm.weight": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.down_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.down_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.down_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.gate_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.gate_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.gate_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.up_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.up_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.123.mlp.up_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.123.post_attention_layernorm.weight": "model-00063-of-00064.safetensors", + "model.layers.123.self_attn.k_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.k_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.k_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.o_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.o_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.o_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.q_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.q_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.q_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.v_proj.biases": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.v_proj.scales": "model-00062-of-00064.safetensors", + "model.layers.123.self_attn.v_proj.weight": "model-00062-of-00064.safetensors", + "model.layers.124.input_layernorm.weight": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.down_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.down_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.down_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.gate_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.gate_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.gate_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.up_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.up_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.124.mlp.up_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.124.post_attention_layernorm.weight": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.k_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.k_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.k_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.o_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.o_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.o_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.q_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.q_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.q_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.v_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.v_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.124.self_attn.v_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.125.input_layernorm.weight": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.down_proj.biases": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.down_proj.scales": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.down_proj.weight": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.gate_proj.biases": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.gate_proj.scales": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.gate_proj.weight": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.up_proj.biases": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.up_proj.scales": "model-00064-of-00064.safetensors", + "model.layers.125.mlp.up_proj.weight": "model-00064-of-00064.safetensors", + "model.layers.125.post_attention_layernorm.weight": "model-00064-of-00064.safetensors", + "model.layers.125.self_attn.k_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.k_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.k_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.o_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.o_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.o_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.q_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.q_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.q_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.v_proj.biases": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.v_proj.scales": "model-00063-of-00064.safetensors", + "model.layers.125.self_attn.v_proj.weight": "model-00063-of-00064.safetensors", + "model.layers.13.input_layernorm.weight": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.down_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.gate_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.up_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00064.safetensors", + "model.layers.13.self_attn.k_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.o_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.q_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.v_proj.biases": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00007-of-00064.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00064.safetensors", + "model.layers.14.input_layernorm.weight": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.down_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.gate_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.up_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.k_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.o_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.q_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.v_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.15.input_layernorm.weight": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.down_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.gate_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.up_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00064.safetensors", + "model.layers.15.self_attn.k_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.o_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.q_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.v_proj.biases": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00008-of-00064.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00064.safetensors", + "model.layers.16.input_layernorm.weight": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.down_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.gate_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.up_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.k_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.o_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.q_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.v_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.17.input_layernorm.weight": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.down_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.gate_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.up_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00064.safetensors", + "model.layers.17.self_attn.k_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.o_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.q_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.v_proj.biases": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00009-of-00064.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00064.safetensors", + "model.layers.18.input_layernorm.weight": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.down_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.gate_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.up_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.k_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.o_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.q_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.v_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.19.input_layernorm.weight": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.down_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.gate_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.up_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00064.safetensors", + "model.layers.19.self_attn.k_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.o_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.q_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.v_proj.biases": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00010-of-00064.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00064.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.down_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.gate_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.up_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.k_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.o_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.q_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.v_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.20.input_layernorm.weight": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.down_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.gate_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.up_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.k_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.o_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.q_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.v_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.21.input_layernorm.weight": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.down_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.gate_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.up_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00064.safetensors", + "model.layers.21.self_attn.k_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.o_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.q_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.v_proj.biases": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00011-of-00064.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00064.safetensors", + "model.layers.22.input_layernorm.weight": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.down_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.gate_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.up_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.k_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.o_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.q_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.v_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.23.input_layernorm.weight": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.down_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.gate_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.up_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00064.safetensors", + "model.layers.23.self_attn.k_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.o_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.q_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.v_proj.biases": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00012-of-00064.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00064.safetensors", + "model.layers.24.input_layernorm.weight": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.down_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.gate_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.up_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.k_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.o_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.q_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.v_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.25.input_layernorm.weight": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.down_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.gate_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.up_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00064.safetensors", + "model.layers.25.self_attn.k_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.o_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.q_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.v_proj.biases": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00013-of-00064.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00064.safetensors", + "model.layers.26.input_layernorm.weight": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.down_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.gate_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.up_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.k_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.o_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.q_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.v_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.27.input_layernorm.weight": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.down_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.gate_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.up_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00064.safetensors", + "model.layers.27.self_attn.k_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.o_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.q_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.v_proj.biases": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00014-of-00064.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00064.safetensors", + "model.layers.28.input_layernorm.weight": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.down_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.gate_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.up_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.k_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.o_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.q_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.v_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.29.input_layernorm.weight": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.down_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.gate_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.up_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00064.safetensors", + "model.layers.29.self_attn.k_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.o_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.q_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.v_proj.biases": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00015-of-00064.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00015-of-00064.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.down_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.gate_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.up_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00064.safetensors", + "model.layers.3.self_attn.k_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.o_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.q_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.v_proj.biases": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00002-of-00064.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00064.safetensors", + "model.layers.30.input_layernorm.weight": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.down_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.gate_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.up_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.k_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.o_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.q_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.v_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.31.input_layernorm.weight": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.down_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.gate_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.up_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00064.safetensors", + "model.layers.31.self_attn.k_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.o_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.q_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.v_proj.biases": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00016-of-00064.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00064.safetensors", + "model.layers.32.input_layernorm.weight": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.down_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.gate_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.up_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.k_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.o_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.q_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.v_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.33.input_layernorm.weight": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.down_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.gate_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.up_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00064.safetensors", + "model.layers.33.self_attn.k_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.o_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.q_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.v_proj.biases": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00017-of-00064.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00064.safetensors", + "model.layers.34.input_layernorm.weight": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.down_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.gate_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.up_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.k_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.o_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.q_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.v_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.35.input_layernorm.weight": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.down_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.gate_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.up_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00064.safetensors", + "model.layers.35.self_attn.k_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.o_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.q_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.v_proj.biases": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00018-of-00064.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00064.safetensors", + "model.layers.36.input_layernorm.weight": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.down_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.gate_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.up_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.k_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.o_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.q_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.v_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.37.input_layernorm.weight": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.down_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.gate_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.up_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00064.safetensors", + "model.layers.37.self_attn.k_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.o_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.q_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.v_proj.biases": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00019-of-00064.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00064.safetensors", + "model.layers.38.input_layernorm.weight": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.down_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.gate_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.up_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.k_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.o_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.q_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.v_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.39.input_layernorm.weight": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.down_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.gate_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.up_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00021-of-00064.safetensors", + "model.layers.39.self_attn.k_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.o_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.q_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.v_proj.biases": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00020-of-00064.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00064.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.down_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.gate_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.up_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.k_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.o_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.q_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.v_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.40.input_layernorm.weight": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.down_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.gate_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.up_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.k_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.o_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.q_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.v_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.41.input_layernorm.weight": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.down_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.gate_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.up_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00064.safetensors", + "model.layers.41.self_attn.k_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.o_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.q_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.v_proj.biases": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00021-of-00064.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00021-of-00064.safetensors", + "model.layers.42.input_layernorm.weight": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.down_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.gate_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.up_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.k_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.o_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.q_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.v_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.43.input_layernorm.weight": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.down_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.gate_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.up_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00023-of-00064.safetensors", + "model.layers.43.self_attn.k_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.o_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.q_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.v_proj.biases": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00022-of-00064.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00022-of-00064.safetensors", + "model.layers.44.input_layernorm.weight": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.down_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.gate_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.up_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.k_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.o_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.q_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.v_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.45.input_layernorm.weight": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.down_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.gate_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.up_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00024-of-00064.safetensors", + "model.layers.45.self_attn.k_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.o_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.q_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.v_proj.biases": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00023-of-00064.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00023-of-00064.safetensors", + "model.layers.46.input_layernorm.weight": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.down_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.gate_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.up_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.k_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.o_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.q_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.v_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.47.input_layernorm.weight": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.down_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.gate_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.up_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00025-of-00064.safetensors", + "model.layers.47.self_attn.k_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.o_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.q_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.v_proj.biases": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00024-of-00064.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00024-of-00064.safetensors", + "model.layers.48.input_layernorm.weight": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.down_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.down_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.gate_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.gate_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.up_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.up_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.k_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.o_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.q_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.v_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.49.input_layernorm.weight": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.down_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.down_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.gate_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.gate_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.up_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.up_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00026-of-00064.safetensors", + "model.layers.49.self_attn.k_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.o_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.q_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.v_proj.biases": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00025-of-00064.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00025-of-00064.safetensors", + "model.layers.5.input_layernorm.weight": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.down_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.gate_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.up_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00064.safetensors", + "model.layers.5.self_attn.k_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.o_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.q_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.v_proj.biases": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00003-of-00064.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00064.safetensors", + "model.layers.50.input_layernorm.weight": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.down_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.down_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.gate_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.gate_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.up_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.up_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.k_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.o_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.q_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.v_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.51.input_layernorm.weight": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.down_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.down_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.gate_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.gate_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.up_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.up_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00027-of-00064.safetensors", + "model.layers.51.self_attn.k_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.o_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.q_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.v_proj.biases": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00026-of-00064.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00064.safetensors", + "model.layers.52.input_layernorm.weight": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.down_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.down_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.gate_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.gate_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.up_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.up_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.k_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.o_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.q_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.v_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.53.input_layernorm.weight": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.down_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.down_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.gate_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.gate_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.up_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.up_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00028-of-00064.safetensors", + "model.layers.53.self_attn.k_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.o_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.q_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.v_proj.biases": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00027-of-00064.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00027-of-00064.safetensors", + "model.layers.54.input_layernorm.weight": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.down_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.down_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.gate_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.gate_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.up_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.up_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.k_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.o_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.q_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.v_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.55.input_layernorm.weight": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.down_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.down_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.gate_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.gate_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.up_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.up_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00029-of-00064.safetensors", + "model.layers.55.self_attn.k_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.o_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.q_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.v_proj.biases": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00028-of-00064.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00028-of-00064.safetensors", + "model.layers.56.input_layernorm.weight": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.down_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.down_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.gate_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.gate_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.up_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.up_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.k_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.o_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.q_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.v_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.57.input_layernorm.weight": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.down_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.down_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.gate_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.gate_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.up_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.up_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00030-of-00064.safetensors", + "model.layers.57.self_attn.k_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.o_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.q_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.v_proj.biases": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00029-of-00064.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00029-of-00064.safetensors", + "model.layers.58.input_layernorm.weight": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.down_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.down_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.gate_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.gate_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.up_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.up_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.k_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.o_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.q_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.v_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.59.input_layernorm.weight": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.down_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.down_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.gate_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.gate_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.up_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.up_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00031-of-00064.safetensors", + "model.layers.59.self_attn.k_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.o_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.q_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.v_proj.biases": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00030-of-00064.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00030-of-00064.safetensors", + "model.layers.6.input_layernorm.weight": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.down_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.gate_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.up_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.k_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.o_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.q_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.v_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.60.input_layernorm.weight": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.down_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.down_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.gate_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.gate_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.up_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.up_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.k_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.k_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.o_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.o_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.q_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.q_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.v_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.v_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.61.input_layernorm.weight": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.down_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.down_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.gate_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.gate_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.up_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.up_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00032-of-00064.safetensors", + "model.layers.61.self_attn.k_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.k_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.o_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.o_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.q_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.q_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.v_proj.biases": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.v_proj.scales": "model-00031-of-00064.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00031-of-00064.safetensors", + "model.layers.62.input_layernorm.weight": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.down_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.down_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.gate_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.gate_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.up_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.up_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.k_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.k_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.o_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.o_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.q_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.q_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.v_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.v_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.63.input_layernorm.weight": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.down_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.down_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.gate_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.gate_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.up_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.up_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00033-of-00064.safetensors", + "model.layers.63.self_attn.k_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.k_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.o_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.o_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.q_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.q_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.v_proj.biases": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.v_proj.scales": "model-00032-of-00064.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00032-of-00064.safetensors", + "model.layers.64.input_layernorm.weight": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.down_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.down_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.gate_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.gate_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.up_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.up_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.k_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.k_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.o_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.o_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.q_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.q_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.v_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.v_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.65.input_layernorm.weight": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.down_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.down_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.gate_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.gate_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.up_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.up_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00034-of-00064.safetensors", + "model.layers.65.self_attn.k_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.k_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.o_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.o_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.q_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.q_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.v_proj.biases": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.v_proj.scales": "model-00033-of-00064.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00033-of-00064.safetensors", + "model.layers.66.input_layernorm.weight": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.down_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.down_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.gate_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.gate_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.up_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.up_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.k_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.k_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.o_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.o_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.q_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.q_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.v_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.v_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.67.input_layernorm.weight": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.down_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.down_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.gate_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.gate_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.up_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.up_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00035-of-00064.safetensors", + "model.layers.67.self_attn.k_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.k_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.o_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.o_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.q_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.q_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.v_proj.biases": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.v_proj.scales": "model-00034-of-00064.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00034-of-00064.safetensors", + "model.layers.68.input_layernorm.weight": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.down_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.down_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.gate_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.gate_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.up_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.up_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.k_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.k_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.o_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.o_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.q_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.q_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.v_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.v_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.69.input_layernorm.weight": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.down_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.down_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.gate_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.gate_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.up_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.up_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00036-of-00064.safetensors", + "model.layers.69.self_attn.k_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.k_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.o_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.o_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.q_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.q_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.v_proj.biases": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.v_proj.scales": "model-00035-of-00064.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00035-of-00064.safetensors", + "model.layers.7.input_layernorm.weight": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.down_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.gate_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.up_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00064.safetensors", + "model.layers.7.self_attn.k_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.o_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.q_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.v_proj.biases": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00004-of-00064.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00064.safetensors", + "model.layers.70.input_layernorm.weight": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.down_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.down_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.gate_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.gate_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.up_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.up_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.k_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.k_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.o_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.o_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.q_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.q_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.v_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.v_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.71.input_layernorm.weight": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.down_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.down_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.gate_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.gate_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.up_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.up_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00037-of-00064.safetensors", + "model.layers.71.self_attn.k_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.k_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.o_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.o_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.q_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.q_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.v_proj.biases": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.v_proj.scales": "model-00036-of-00064.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00036-of-00064.safetensors", + "model.layers.72.input_layernorm.weight": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.down_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.down_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.gate_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.gate_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.up_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.up_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.k_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.k_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.o_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.o_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.q_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.q_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.v_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.v_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.73.input_layernorm.weight": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.down_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.down_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.gate_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.gate_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.up_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.up_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00038-of-00064.safetensors", + "model.layers.73.self_attn.k_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.k_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.o_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.o_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.q_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.q_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.v_proj.biases": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.v_proj.scales": "model-00037-of-00064.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00037-of-00064.safetensors", + "model.layers.74.input_layernorm.weight": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.down_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.down_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.gate_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.gate_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.up_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.up_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.k_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.k_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.o_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.o_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.q_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.q_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.v_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.v_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.75.input_layernorm.weight": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.down_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.down_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.gate_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.gate_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.up_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.up_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00039-of-00064.safetensors", + "model.layers.75.self_attn.k_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.k_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.o_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.o_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.q_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.q_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.v_proj.biases": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.v_proj.scales": "model-00038-of-00064.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00038-of-00064.safetensors", + "model.layers.76.input_layernorm.weight": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.down_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.down_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.gate_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.gate_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.up_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.up_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.k_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.k_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.o_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.o_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.q_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.q_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.v_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.v_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.77.input_layernorm.weight": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.down_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.down_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.gate_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.gate_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.up_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.up_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00040-of-00064.safetensors", + "model.layers.77.self_attn.k_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.k_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.o_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.o_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.q_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.q_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.v_proj.biases": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.v_proj.scales": "model-00039-of-00064.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00039-of-00064.safetensors", + "model.layers.78.input_layernorm.weight": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.down_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.down_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.gate_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.gate_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.up_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.up_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.k_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.k_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.o_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.o_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.q_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.q_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.v_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.v_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.79.input_layernorm.weight": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.down_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.down_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.gate_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.gate_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.up_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.up_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00041-of-00064.safetensors", + "model.layers.79.self_attn.k_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.k_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.o_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.o_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.q_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.q_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.v_proj.biases": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.v_proj.scales": "model-00040-of-00064.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00040-of-00064.safetensors", + "model.layers.8.input_layernorm.weight": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.down_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.gate_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.up_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.k_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.o_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.q_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.v_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.80.input_layernorm.weight": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.down_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.down_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.down_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.gate_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.gate_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.gate_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.up_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.up_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.80.mlp.up_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.k_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.k_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.o_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.o_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.q_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.q_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.v_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.v_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.81.input_layernorm.weight": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.down_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.down_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.down_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.gate_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.gate_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.gate_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.up_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.up_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.81.mlp.up_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00042-of-00064.safetensors", + "model.layers.81.self_attn.k_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.k_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.o_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.o_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.q_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.q_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.v_proj.biases": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.v_proj.scales": "model-00041-of-00064.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00041-of-00064.safetensors", + "model.layers.82.input_layernorm.weight": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.down_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.down_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.down_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.gate_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.gate_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.gate_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.up_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.up_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.82.mlp.up_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.k_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.k_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.o_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.o_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.q_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.q_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.v_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.v_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.83.input_layernorm.weight": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.down_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.down_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.down_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.gate_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.gate_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.gate_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.up_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.up_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.83.mlp.up_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00043-of-00064.safetensors", + "model.layers.83.self_attn.k_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.k_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.o_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.o_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.q_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.q_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.v_proj.biases": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.v_proj.scales": "model-00042-of-00064.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00042-of-00064.safetensors", + "model.layers.84.input_layernorm.weight": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.down_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.down_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.down_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.gate_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.gate_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.gate_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.up_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.up_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.84.mlp.up_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.k_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.k_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.o_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.o_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.q_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.q_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.v_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.v_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.85.input_layernorm.weight": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.down_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.down_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.down_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.gate_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.gate_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.gate_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.up_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.up_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.85.mlp.up_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00044-of-00064.safetensors", + "model.layers.85.self_attn.k_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.k_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.o_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.o_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.q_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.q_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.v_proj.biases": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.v_proj.scales": "model-00043-of-00064.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00043-of-00064.safetensors", + "model.layers.86.input_layernorm.weight": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.down_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.down_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.down_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.gate_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.gate_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.gate_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.up_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.up_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.86.mlp.up_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.k_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.k_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.o_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.o_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.q_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.q_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.v_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.v_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.87.input_layernorm.weight": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.down_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.down_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.down_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.gate_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.gate_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.gate_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.up_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.up_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.87.mlp.up_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00045-of-00064.safetensors", + "model.layers.87.self_attn.k_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.k_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.o_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.o_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.q_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.q_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.v_proj.biases": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.v_proj.scales": "model-00044-of-00064.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00044-of-00064.safetensors", + "model.layers.88.input_layernorm.weight": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.down_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.down_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.down_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.gate_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.gate_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.gate_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.up_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.up_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.88.mlp.up_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.k_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.k_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.o_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.o_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.q_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.q_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.v_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.v_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.89.input_layernorm.weight": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.down_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.down_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.down_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.gate_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.gate_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.gate_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.up_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.up_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.89.mlp.up_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00046-of-00064.safetensors", + "model.layers.89.self_attn.k_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.k_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.o_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.o_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.q_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.q_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.v_proj.biases": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.v_proj.scales": "model-00045-of-00064.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00045-of-00064.safetensors", + "model.layers.9.input_layernorm.weight": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.down_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.gate_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.up_proj.biases": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00006-of-00064.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00006-of-00064.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00064.safetensors", + "model.layers.9.self_attn.k_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.o_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.q_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.v_proj.biases": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00005-of-00064.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00064.safetensors", + "model.layers.90.input_layernorm.weight": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.down_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.down_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.down_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.gate_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.gate_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.gate_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.up_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.up_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.90.mlp.up_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.k_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.k_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.o_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.o_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.q_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.q_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.v_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.v_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.91.input_layernorm.weight": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.down_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.down_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.down_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.gate_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.gate_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.gate_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.up_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.up_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.91.mlp.up_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00047-of-00064.safetensors", + "model.layers.91.self_attn.k_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.k_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.o_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.o_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.q_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.q_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.v_proj.biases": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.v_proj.scales": "model-00046-of-00064.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00046-of-00064.safetensors", + "model.layers.92.input_layernorm.weight": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.down_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.down_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.down_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.gate_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.gate_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.gate_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.up_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.up_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.92.mlp.up_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.92.post_attention_layernorm.weight": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.k_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.k_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.k_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.o_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.o_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.o_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.q_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.q_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.q_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.v_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.v_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.92.self_attn.v_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.93.input_layernorm.weight": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.down_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.down_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.down_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.gate_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.gate_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.gate_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.up_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.up_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.93.mlp.up_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.93.post_attention_layernorm.weight": "model-00048-of-00064.safetensors", + "model.layers.93.self_attn.k_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.k_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.k_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.o_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.o_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.o_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.q_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.q_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.q_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.v_proj.biases": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.v_proj.scales": "model-00047-of-00064.safetensors", + "model.layers.93.self_attn.v_proj.weight": "model-00047-of-00064.safetensors", + "model.layers.94.input_layernorm.weight": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.down_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.down_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.down_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.gate_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.gate_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.gate_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.up_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.up_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.94.mlp.up_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.94.post_attention_layernorm.weight": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.k_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.k_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.k_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.o_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.o_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.o_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.q_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.q_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.q_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.v_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.v_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.94.self_attn.v_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.95.input_layernorm.weight": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.down_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.down_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.down_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.gate_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.gate_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.gate_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.up_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.up_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.95.mlp.up_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.95.post_attention_layernorm.weight": "model-00049-of-00064.safetensors", + "model.layers.95.self_attn.k_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.k_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.k_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.o_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.o_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.o_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.q_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.q_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.q_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.v_proj.biases": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.v_proj.scales": "model-00048-of-00064.safetensors", + "model.layers.95.self_attn.v_proj.weight": "model-00048-of-00064.safetensors", + "model.layers.96.input_layernorm.weight": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.down_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.down_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.down_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.gate_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.gate_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.gate_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.up_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.up_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.96.mlp.up_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.96.post_attention_layernorm.weight": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.k_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.k_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.k_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.o_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.o_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.o_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.q_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.q_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.q_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.v_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.v_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.96.self_attn.v_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.97.input_layernorm.weight": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.down_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.down_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.down_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.gate_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.gate_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.gate_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.up_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.up_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.97.mlp.up_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.97.post_attention_layernorm.weight": "model-00050-of-00064.safetensors", + "model.layers.97.self_attn.k_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.k_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.k_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.o_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.o_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.o_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.q_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.q_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.q_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.v_proj.biases": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.v_proj.scales": "model-00049-of-00064.safetensors", + "model.layers.97.self_attn.v_proj.weight": "model-00049-of-00064.safetensors", + "model.layers.98.input_layernorm.weight": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.down_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.down_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.down_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.gate_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.gate_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.gate_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.up_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.up_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.98.mlp.up_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.98.post_attention_layernorm.weight": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.k_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.k_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.k_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.o_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.o_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.o_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.q_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.q_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.q_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.v_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.v_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.98.self_attn.v_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.99.input_layernorm.weight": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.down_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.down_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.down_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.gate_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.gate_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.gate_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.up_proj.biases": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.up_proj.scales": "model-00051-of-00064.safetensors", + "model.layers.99.mlp.up_proj.weight": "model-00051-of-00064.safetensors", + "model.layers.99.post_attention_layernorm.weight": "model-00051-of-00064.safetensors", + "model.layers.99.self_attn.k_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.k_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.k_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.o_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.o_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.o_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.q_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.q_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.q_proj.weight": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.v_proj.biases": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.v_proj.scales": "model-00050-of-00064.safetensors", + "model.layers.99.self_attn.v_proj.weight": "model-00050-of-00064.safetensors", + "model.norm.weight": "model-00064-of-00064.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..278b7f0f84be865c4687700ee7b3c63d89a51e18 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..37d7807e935d1462a2f093828ac5ee9a08c628a7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e4573a56ca97b0233ddc2dd63f634aeee35b84f352d2ce2aaa5992735cfcad +size 17209827 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1916c2b20aa070a9deb86df289cd924027e7ac85 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "add_bos_token": true, + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizerFast", + "chat_template": "{%- set thinking_prompt = 'You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside tags, and then provide your solution or response to the problem.' %}\n{%- set standard_prompt = 'You are Hermes, created by Nous Research.' %}\n{%- if not thinking is defined %}{% set thinking = false %}{% endif %}\n{%- if not keep_cots is defined %}{% set keep_cots = false %}{% endif %}\n{%- if thinking %}{%- set system_prompt = thinking_prompt %}{%- else %}{%- set system_prompt = standard_prompt %}{%- endif %}\n{%- if tools %}\n {{- bos_token + '<|start_header_id|>system<|end_header_id|>\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- system_prompt }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou are a function calling AI model. You 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 {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": \\\"\\\", \\\"arguments\\\": }\\n<|eot_id|>\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- bos_token + '<|start_header_id|>system<|end_header_id|>\\n\\n' + messages[0]['content'] + '<|eot_id|>' }}\n {%- else %}\n {{- bos_token + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_prompt + '<|eot_id|>' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\\n\\n' + message.content + '<|eot_id|>' }}\n {%- elif (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\\n' }}\n {%- if message.content %}\n {%- set content = message['content'] -%}\n {%- if thinking %}\n {%- if not keep_cots %}\n {%- set content = ' ' + content.split('', 1)[1] -%}\n {%- endif %}\n {%- endif %}\n {{- '\\n' + content + '<|eot_id|>' }}\n {%- endif %}\n {%- elif message.role == \"assistant\" %}\n {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\\n' }}\n {%- if message.content %}\n {%- set content = message['content'] -%}\n {%- if thinking %}\n {%- if not keep_cots %}\n {%- set content = ' ' + content.split('', 1)[1] -%}\n {%- endif %}\n {%- endif %}\n {{- '\\n' + content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|eot_id|>' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|eot_id|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n" +} \ No newline at end of file