Upload folder using huggingface_hub

.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

chat_template.jinja

@@ -0,0 +1,103 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson|string }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{{ visible_text(m.content) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = ((content.split('</think>')|first).rstrip('\n').split('<think>')|last).lstrip('\n') %}
+        {%- set content = (content.split('</think>')|last).lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson|string if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,44 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "first_k_dense_replace": 3,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1536,
+  "n_group": 1,
+  "n_routed_experts": 160,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 92,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 151330,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 2.5,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.1",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "use_qk_norm": true,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.54.0"
+}

model-00001-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ec0ed85ee95cae5c9b76a7af7272a23169b81705c177c0212f65b24d4b8b41
+size 3753953568

model-00002-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5ed321e28aa0c3d31c1b9a9ac0e5666d915ffd89dff216a34427b33fb03c55
+size 650168352

model-00003-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93996707aea7dc24a24e97eb72a57fbfd2d197a3cab970adf334ed28ae67abb
+size 650168352

model-00004-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76581125a03a274386d8d0cd0e2c84242135bd0b728c33a3b311e1967b53ab7
+size 7871313120

model-00005-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72cdb466003372faf78d647ffec247c33f0f2346177147ecce95e8e50b7b678a
+size 7871313120

model-00006-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e643fc9c4b55c9861a965a744b85ae54453275d7a4dfdfad0ca7a9517ad18011
+size 7871313120

model-00007-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6145a87fc2f1e30123293802181b1c684ac710cdd6c929b2dab145154bbd9b7c
+size 7871313120

model-00008-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c5cfd2f82adabf3db579a5ff217506d0f5e1b7211492ef73b2209bb138f41f
+size 7871313120

model-00009-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e37371e81407fd7b5cd543532c6bdca2bf865a2ee567e8f731777b19a9bd43
+size 7871313120

model-00010-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa2a54871e04125363468a6ca024de373ab38edb6f58b657913c2cd17ce5764
+size 7871313120

model-00011-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c06bc5a93318dcf91a7c60109c08e8df95a9a5130196a683434d9ede437f8
+size 7871313616

model-00012-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa88ebbabdc43302cf19ac2d81b27f2b16a3154fdd9ed096040615fa65013805
+size 7871313616

model-00013-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a222612fd47c6ca8166275e66e723819baa3068eee2e1694f326066ac67ce4
+size 7871313616

model-00014-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8d2da26be63fe9764a4a4cc6a00e58f406aeeda404c31b61612e5e74f9caf8
+size 7871313616

model-00015-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f832318ea861a4841a3ce0886eaa0ca7dee9729f74b5141634d7d7e9d6f2ba9
+size 7871313616

model-00016-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d344913210c96c6695341094e7da2817ccb94f3946ee9698a76eaaaaf60c1b44
+size 7871313616

model-00017-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a4ce3054f3670fd5a7d1e71f502318e65ebb51ee629bd5eccd98adc736d4f6
+size 7871313616

model-00018-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006012f1bf7dd33271f12626000418c43e127b56bc70f3a5e314656ad717f424
+size 7871313616

model-00019-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067349f582d85e7bd9b0326b82ee32cede246cf359b4e0b4c6cfe3f95caf8e21
+size 7871313616

model-00020-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21f395f920d50618e06b473f64971789746d86f3e20e2eab0483562ced51b2a
+size 7871313616

model-00021-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bde74ebffd96f550117c7b297198eadf75fb8c99603b6e78fd6d6bea62a8da8
+size 7871313616

model-00022-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9520583b0947a4bc9e3b22ee93dac2f19256f4f889ae17a5239e4275528db8
+size 7871313616

model-00023-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16613154e9ab024458f9acd079d7345db4a05593c5a596176640d68053665753
+size 7871313616

model-00024-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08d17d951a625b2cac46fcf15d7e4b6a99a28f91befabeb7d361fa7cac01e7b
+size 7871313616

model-00025-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5cbe90ff83f0b2b91c92d5ba2e100263e8306ce3f6381bdd54051a6a8b6c3d
+size 7871313616

model-00026-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea400d62257ef3f0412c8496c955a9ec7052fa4761dfbf4b35905aa04e73318
+size 7871313616

model-00027-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012d00adf402e18bb9a900d5dc549c2c45f047eb486ef2a44517a8e532dd9f2b
+size 7871313616

model-00028-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63de598020c34be07e77fb82319760bd539da4adfc48eecf83f64cc85ac35196
+size 7871313616

model-00029-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebe5474925c2edf5dea140224c9d506147f44c5accded8a854edb7538e88d3a
+size 7871313616

model-00030-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272627d9996b600a934e39c285914c04949e9e9ecbde8ddc2cdc228af5a0be42
+size 7871313616

model-00031-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50b8a452aa3db68fa81daa96d04af6b68aaaf2d9565e2b65ce427fbf821d6573
+size 7871313616

model-00032-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bc051e0ed087b3bcfaba48ecc5a2dab369ec95d0bc43b779daec146b9ab45b
+size 7871313616

model-00033-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d506e1a1ac6faea9b46ece2be12d1d83d3e6987d8c836b0deebdb77a96baeac0
+size 7871313616

model-00034-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b67f3dfb65d866d6dadeb3b33709641bdf93b34e5cd50ab480f08ca2fe1ab2
+size 7871313616

model-00035-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5187967ed92ebd28040749a6735e6dc5b5b7a921f26ecc320db909b1af3fab
+size 7871313616

model-00036-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5babc5b903c4e8f30a014d6f63fe679331776eb8e19e1807099604085e506349
+size 7871313616

model-00037-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8696f7e938ddd6a8a578467302b58907106add63ec9d06ada3f58db1e1f35b8a
+size 7871313616

model-00038-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ad1eda9008b3cca972e8c7637aba3bf598daba0f5f7146fcf70656d6807291
+size 7871313616

model-00039-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc174288c0a6dfe1ed30e7b9d0b14b4008cef1c44121ecba5d3fc5711f9ffcf
+size 7871313616

model-00040-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bc1f191e6ece41ac959fae053e56c8d9b7aae4e248396db308df192b0dfdca
+size 7871313616

model-00041-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1086567592913cf955a099e6bd36d69803197a5e737895e82d27e139ee797454
+size 7871313616

model-00042-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd01aed8bd9f3875c999a912c10806379df34083c8d5ea86dbeed586218404e5
+size 7871313616

model-00043-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3757974e615f565fb9179ca721617f92c1c46e02cb27de2173ccf69851a4bbe5
+size 7871313616

model-00044-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333883124d4baa2d0ad5527832875418c574a9bb9d022184573d73da6b0450bb
+size 7871313616

model-00045-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2347fda76deadd548681a1b96d6868eed8c00a37808ece8ff71011a54989c091
+size 7871313616

model-00046-of-00093.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be1386859ce861008c1f5333277a91e9b76dd522f4316edc25d5bf48e18934b
+size 7871313616