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

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1753847623

README.md

@@ -0,0 +1,105 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- glm4_moe
+- GPTQ
+- Int4-Int8Mix
+- 量化修复
+- vLLM
+base_model:
+  - ZhipuAI/GLM-4.5-Air
+base_model_relation: quantized
+---
+# GLM-4.5-Air-GPTQ-Int4-Int8Mix
+基础型 [ZhipuAI/GLM-4.5-Air](https://www.modelscope.cn/models/ZhipuAI/GLM-4.5-Air)
+
+
+### 【Vllm 单机8卡启动命令】
+<i>注: 启动该模型一定要跟`--enable-expert-parallel` ，否则其专家张量TP整除除不尽；即使是2卡也需要。 </i>
+```
+$CONTEXT_LENGTH=32768
+
+vllm serve \
+    tclf90/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
+    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
+    --enable-expert-parallel \
+    --swap-space 16 \
+    --max-num-seqs 512 \
+    --max-model-len $CONTEXT_LENGTH \
+    --max-seq-len-to-capture $CONTEXT_LENGTH \
+    --gpu-memory-utilization 0.9 \
+    --tensor-parallel-size 8 \
+    --trust-remote-code \
+    --disable-log-requests \
+    --host 0.0.0.0 \
+    --port 8000
+```
+
+### 【依赖】
+
+```
+vllm==0.10.0
+```
+
+### 【模型更新日期】
+``` 
+2025-07-30
+1. 首次commit
+```
+
+### 【模型列表】
+
+| 文件大小   | 最近更新时间       |
+|--------|--------------|
+| `67GB` | `2025-07-30` |
+
+
+
+### 【模型下载】
+
+```python
+from modelscope import snapshot_download
+snapshot_download('tclf90/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="本地路径")
+```
+
+
+### 【介绍】
+
+# GLM-4.5
+
+<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">
+    👋 加入我们的<a href="https://github.com/zai-org/GLM-4.5/blob/main/resources/WECHAT.md" target="_blank"> 微信群 </a>。
+    <br>
+    📖 查看GLM-4.5<a href="https://z.ai/blog/glm-4.5" target="_blank"> 技术博客 </a>。
+    <br>
+    📍 在<a href="https://docs.bigmodel.cn/cn/guide/models/text/glm-4.5"> 智谱AI开放平台 </a>上使用GLM-4.5 API服务。
+    <br>
+    👉 一键体验 <a href="https://chat.z.ai" >GLM-4.5 </a>。
+</p>
+
+## 模型介绍
+
+**GLM-4.5** 系列模型是专为智能体设计的基础模型。GLM-4.5拥有 **3550** 亿总参数量，其中 **320** 亿活跃参数；GLM-4.5-Air采用更紧凑的设计，拥有
+ **1060** 亿总参数量，其中 **120** 亿活跃参数。GLM-4.5模型统一了推理、编码和智能体能力，以满足智能体应用的复杂需求。
+
+GLM-4.5 和 GLM-4.5-Air 都是混合推理模型，提供两种模式：用于复杂推理和工具使用的思考模式，以及用于即时响应的非思考模式。
+
+我们已开源了 GLM-4.5 和 GLM-4.5-Air 的基础模型、混合推理模型以及混合推理模型的FP8版本。它们采用MIT开源许可证发布，可用于商业用途和二次开发。
+
+在我们对12项行业标准基准的全面评估中，GLM-4.5表现卓越，得分 **63.2**，在所有专有和开源模型中排名**第3**
+。值得注意的是，GLM-4.5-Air在保持优异效率的同时，仍取得了 **59.8** 的竞争性成绩。
+
+![bench](https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/bench.png)
+
+如需了解更多评估结果、展示案例和技术细节，请访问我们的 [技术博客](https://z.ai/blog/glm-4.5)。技术报告将很快发布。
+
+模型代码、工具解析器和推理解析器可在 [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)
+和 [SGLang](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/glm4_moe.py) 的实现中找到。
+
+## 快速开始
+
+请参考我们的[github](https://github.com/zai-org/GLM-4.5)项目。

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 +1,60 @@
+{
+  "name_or_path": "tclf90/GLM-4.5-Air-GPTQ-Int4-Int8Mix",
+  "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": 11264,
+  "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": "float16",
+  "transformers_version": "4.54.0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 151552,
+  "quantization_config": {
+    "quant_method": "gptq_marlin",
+    "bits": 4,
+    "group_size": 128,
+    "sym": true,
+    "desc_act": false,
+    "dynamic": {
+      "-:model.embed_tokens.weight": {},
+      "-:.*shared_experts": {},
+      "-:.*shared_head": {},
+      "-:lm_head.weight": {},
+      "+:model[.]layers[.]([0-4]|4[4-6])[.].*": {
+        "bits": 8
+      }
+    }
+  }
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e801e5ba362855c9eae5174c9413d6393507f9feab5d8752f296cdded26687
+size 4996300592

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c016a9c08a89a576ab46a15c6e0af628343f0249b00eb5056a22d9892309b2c9
+size 4997241512

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2e80b7f452d3dda9d43fe6f188cf2b872d8dcaa8f8e4708d392cda70a30308
+size 4999482888

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e44b9d227f7ec156707d44fa8eb13d08d2cf0085c8b571c2e28ebe368af961d
+size 4998434648

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b292eeaf08bfe53c8f0d8e4e0f858ad56f6733b2d7b458a14f7931075657c452
+size 4998449992

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1493675971ae6b73f96f234e43714c20c5a8c6090745af3781cb5c6612398c
+size 4998439232

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d55438ad27a5cf42760f56f3ece76960bc35f29a1450f4b2e1123c52fbdda3
+size 4998439232

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4746a72dbc1a7584629f9377d1e985777916108667482dfad64d83dff10b0b7
+size 4998449992

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0337c656faad0a6500e2b82d0e5eb3f95111f7b7b02b9f24b8e86a651e426af
+size 4998439232

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f143bc8469c5b7f46060d299cb2e4b5370686349598cc1fafc08345545f699de
+size 4998439224

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b526125c9a02bc81330bf4ef357b789ac3f20faabe9742ae5f19fc2b94aa027
+size 4998449992

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d0d6313c5ee25ba0ed3bd85e7ed9bdb5700dcaf72b3673dc172d153c589be1
+size 4998439240

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49159948785dbb4b3dd01d1f9377b18fae452098da57db3f8e335ddc63d404c3
+size 4994983976

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e430d70f47eaae6ffd0b8896f05dffd4e21ecdca60f3a9c10605570d9d95bc0
+size 4999508280

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03712679108f07582fed478a06d33553a8ec8fed4b7fac08ff3b8859bee668f8
+size 922342368

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd
+size 19970699

tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151343": {
+      "content": "<|begin_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|end_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151345": {
+      "content": "<|begin_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151346": {
+      "content": "<|end_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151347": {
+      "content": "<|code_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151348": {
+      "content": "<|code_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151349": {
+      "content": "<|code_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151350": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151351": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151352": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151353": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151354": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151355": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151356": {
+      "content": "<arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151357": {
+      "content": "</arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151358": {
+      "content": "<arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151359": {
+      "content": "</arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151360": {
+      "content": "/nothink",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151361": {
+      "content": "<|begin_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151362": {
+      "content": "<|end_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151363": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151364": {
+      "content": "<|video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}