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

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "pad_token_id": 151329,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "partial_rotary_factor": 0.5,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "n_group": 1,
+  "topk_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "routed_scaling_factor": 1.0,
+  "num_experts_per_tok": 8,
+  "first_k_dense_replace": 1,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "num_nextn_predict_layers": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 151552
+}

README.md

@@ -1,3 +1,44 @@
----
-license: mit
----
+---
+language:
+- en
+- zh
+library_name: transformers
+license: mit
+pipeline_tag: text-generation
+---
+
+# GLM-4.5-Air
+
+<div align="center">
+<img src=https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/logo.svg width="15%"/>
+</div>
+<p align="center">
+    👋 Join our <a href="https://discord.gg/QR7SARHRxK" target="_blank">Discord</a> community.
+    <br>
+    📖 Check out the GLM-4.5 <a href="https://z.ai/blog/glm-4.5" target="_blank">technical blog</a>, <a href="https://arxiv.org/abs/2508.06471" target="_blank">technical report</a>, and <a href="https://zhipu-ai.feishu.cn/wiki/Gv3swM0Yci7w7Zke9E0crhU7n7D" target="_blank">Zhipu AI technical documentation</a>.
+    <br>
+    📍 Use GLM-4.5 API services on <a href="https://docs.z.ai/guides/llm/glm-4.5">Z.ai API Platform (Global)</a> or <br> <a href="https://docs.bigmodel.cn/cn/guide/models/text/glm-4.5">Zhipu AI Open Platform (Mainland China)</a>.
+    <br>
+    👉 One click to <a href="https://chat.z.ai">GLM-4.5</a>.
+</p>
+  
+## Model Introduction
+
+The **GLM-4.5** series models are foundation models designed for intelligent agents. GLM-4.5 has **355** billion total parameters with **32** billion active parameters, while GLM-4.5-Air adopts a more compact design with **106** billion total parameters and **12** billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.
+
+Both GLM-4.5 and GLM-4.5-Air are hybrid reasoning models that provide two modes: thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses.
+
+We have open-sourced the base models, hybrid reasoning models, and FP8 versions of the hybrid reasoning models for both GLM-4.5 and GLM-4.5-Air. They are released under the MIT open-source license and can be used commercially and for secondary development.
+
+As demonstrated in our comprehensive evaluation across 12 industry-standard benchmarks, GLM-4.5 achieves exceptional performance with a score of **63.2**, in the **3rd** place among all the proprietary and open-source  models. Notably, GLM-4.5-Air delivers competitive results at **59.8** while maintaining superior efficiency.
+
+![bench](https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/bench.png)
+
+For more eval results, show cases, and technical details, please visit
+our [technical blog](https://z.ai/blog/glm-4.5) or [technical report](https://huggingface.co/papers/2508.06471).
+
+The model code, tool parser and reasoning parser can be found in the implementation of [transformers](https://github.com/huggingface/transformers/tree/main/src/transformers/models/glm4_moe), [vLLM](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/glm4_moe_mtp.py) and [SGLang](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/glm4_moe.py).
+
+## Quick Start
+
+Please refer our [github page](https://github.com/zai-org/GLM-4.5) for more detail.

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(ensure_ascii=False) }}
+{% 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>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].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(ensure_ascii=False) 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 +1,43 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "pad_token_id": 151329,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "partial_rotary_factor": 0.5,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "n_group": 1,
+  "topk_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "routed_scaling_factor": 1.0,
+  "num_experts_per_tok": 8,
+  "first_k_dense_replace": 1,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "num_nextn_predict_layers": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "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-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc90f1327c0955805a9c71a44986ed8cdb9ac994a8cf016512672e19d13b58af
+size 2970138176

model-00002-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e36cb4190e6939b7577285872c363d81b55a938208c6eff962749b5e27ea138
+size 4683035216

model-00003-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05118eb58b6595b04a5b1ffddd67574d2952131c15011d59c07db04aec337a01
+size 4683035216

model-00004-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa5802e8c87149ce1c7cfd377185ab3a01ffe45b9bcb8550d6bcd453c18e315
+size 4683035216

model-00005-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42dffc8b0cf8e2f342a83f441cd83162e90cc513c935c3fef0cb5da2b451432
+size 4683035216

model-00006-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e0ff8c88721402092dbcdf24fa42a462ba2290b0d5740b65d4e30fd6915d4b
+size 4683035216

model-00007-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a910716138c8a502757109ceb778e66c1c5721675ad7dec84d41700719905c
+size 4683035216

model-00008-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626fb4167b400f93d8908f34fb0de3d91b738d27200b25ddf607cd1376b577e9
+size 4683035216

model-00009-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0a936ded320cfc53b6be154c04542c63fd97a8571321c3903ebd7c729f7a23
+size 4683035216

model-00010-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60930cea4c1130819cb74d9b185e8b2fbd6b9c5f88aa502a44924f52139afc7c
+size 4683035216

model-00011-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff9c940460ceb829302751106da56561117e3d921f5268c4adc481021ca1af3
+size 4683035616

model-00012-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80861b619e1324e1ef104ca7f68bcd21102de0342276cc8ced55b6db4031512e
+size 4683035616

model-00013-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f18fab81562175d5c4ab790336c06823be7b1932a0cef9e1e0e775f4082c865
+size 4683035616

model-00014-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c9ef7d9e859743708a2f4b8d8ead2b0bd167d23b414d900194af51d09ffc84
+size 4683035616

model-00015-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f41b33f41680fefced4461ed9d05c220706a94d62394fe7355901e25d4f902
+size 4683035616

model-00016-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9783b163dcdb353dde6360beb41e290759121b1374f743d7ef49d8d641df68f
+size 4683035616

model-00017-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374e0861feef49c447d4e2b8910ed6872f6dcc8d42ec10da702e8ea6f4986fdf
+size 4683035616

model-00018-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90cd7ec58fc6918b842233614a073342b8af6a4ef1a4dbb542255d8bfa087292
+size 4683035616

model-00019-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95af937cac1013761be187b97983d115ae2b2a15bae137de3197386263e260e
+size 4683035616

model-00020-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db1aa0a825bbe3bccc37cbbc91cdef457c484760dc2b58e97f0e3c90974ef3a
+size 4683035616

model-00021-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b93985c021b1c9a6e682c7cc2416d68fb5c78d9fb26ba7bda7c6f1aae02bc5
+size 4683035616

model-00022-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3b1f1714e2e6ae2b4928bc84a9eb63fcb227b84d8d3def51dc6e90cfc10026
+size 4683035616

model-00023-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd48b69d29ed7e60363f8025318c6c8c3ccff9b820c11dfcb0da228d82703ab
+size 4683035616

model-00024-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee19b83a1934084acbc36831d98db7015c37fc4373d511fb6b026f7e075e422c
+size 4683035616

model-00025-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc86f79a693eb61932f1d3f86417e1a304d15bee25156a5d363b232941671b73
+size 4683035616

model-00026-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8048fcc96f883f76c9a411a7d302159c38bcf3f375ed8fbc4384a43ad0cb1f8e
+size 4683035616

model-00027-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932893d7a3dc8182d1689d0130fd640e1538edda4059e18d8618dd7d4ee6bca6
+size 4683035616

model-00028-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b152a2aacc535610dc334b19d8b3182f8296e939641b7496223510e8fee735
+size 4683035616

model-00029-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be1e7c104760c2f6ffecfd67ea79f49d3e5ac91cc77922252fb242c560d3f87
+size 4683035616

model-00030-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02653bbbcc0adddb1210a76b255fde8ebc7a14a33ffe8bf452b370f976705b34
+size 4683035616

model-00031-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d60cab81be883b6b6822c967460c3428b55578882f6e1f9d24ffe908516be5a
+size 4683035616

model-00032-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4dd56b06e494a600971340191c428cd90feb2d2436e7a330b12fa1df89a475
+size 4683035616

model-00033-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e671a2115825a264aa8875d526ad71e9e1449e308aca35cb1cbac32d4d1ca3
+size 4683035616

model-00034-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b089b2f7b57eb097fbaa1deb075c341997e7c187ee8bd92d320fbc0645fc3bf5
+size 4683035616

model-00035-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14407dd9b5dba84e6341b1490c566ac18e7a9a370ebeb082fcb04e47e274da2e
+size 4683035616

model-00036-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e230fd38a8bf2f40f6db6ce98c05e2b31b774be70e0f0c7f99dbd2fa8316b889
+size 4683035616

model-00037-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcbc54edd90895693f5ffd188ddce9f14d2c3384989b0d133f1034ccd060bc1
+size 4683035616

model-00038-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bb40880f8dcd3db75f7ed6d8cf77898c232769d751f55d1ea499a28a8b4d67
+size 4683035616

model-00039-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0a59b1923ac1eb830a32f1af0ba1e18d91b122fa0044a8bb1d0386b859af3a
+size 4683035616

model-00040-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618f09f304ad77576dcd0e3ac0614551c0fdb24adc540e7c052a171e0fabb3d2
+size 4683035616

model-00041-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d0d3b5d180251c3a1cbea4b17bd5b33afdf5572c5a38067d5c0526c5cca184
+size 4683035616

model-00042-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19c7df42dbf0cd0b20e88ded99a0a9527778829fd3743ad5181d73a809b29ce
+size 4683035616

model-00043-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26e5e9ca91ea1e7ec91fa79b9d136e5b1c55fc2e0f986cc417a781fd1c1f8e3
+size 4683035616