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:1751586428

README.md

@@ -0,0 +1,103 @@
+---
+license: mit
+pipeline_tag: text-generation
+tags:
+- glm4v
+- GPTQ
+- Int4-Int8Mix
+- vLLM
+base_model:
+  - ZhipuAI/GLM-4.1V-9B-Thinking
+base_model_relation: quantized
+---
+# GLM-4.1V-9B-Thinking-GPTQ-Int4-Int8Mix
+基础型 [ZhipuAI/GLM-4.1V-9B-Thinking](https://www.modelscope.cn/models/ZhipuAI/GLM-4.1V-9B-Thinking)
+
+### 【模型更新日期】
+``` 
+2025-07-03
+1. 首次commit
+2. 确定支持1、2、4卡的`tensor-parallel-size`启动
+```
+
+### 【依赖】
+
+```
+vllm==0.9.2
+```
+
+<div style="
+    background: rgba(255, 193, 61, 0.15);
+    padding: 16px;
+    border-radius: 6px;
+    border: 1px solid rgba(255, 165, 0, 0.3);
+    margin: 16px 0;
+">
+### 【💡2025-07-03 临时安装命令💡】
+
+```
+pip3 install -r requirements.txt
+git clone https://github.com/zRzRzRzRzRzRzR/vllm.git
+cd vllm
+git checkout glm4_1-v
+VLLM_USE_PRECOMPILED=1 pip install --editable .
+```
+</div>
+
+
+### 【模型列表】
+
+| 文件大小    | 最近更新时间       |
+|---------|--------------|
+| `8.9GB` | `2025-07-03` |
+
+
+
+### 【模型下载】
+
+```python
+from modelscope import snapshot_download
+snapshot_download('tclf90/GLM-4.1V-9B-Thinking-GPTQ-Int4-Int8Mix', cache_dir="本地路径")
+```
+
+
+### 【介绍】
+# GLM-4.1V-9B-Thinking
+
+<div align="center">
+<img src=https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/99c5eb6563236f0ff43605d91d107544da9863b2/resources/logo.svg width="40%"/>
+</div>
+<p align="center">
+    📖 查看 GLM-4.1V-9B-Thinking <a href="https://arxiv.org/abs/2507.01006" target="_blank">论文</a> 。
+    <br>
+    💡 立即在线体验 <a href="https://huggingface.co/spaces/THUDM/GLM-4.1V-9B-Thinking-Demo" target="_blank">Hugging Face</a> 或 <a href="https://modelscope.cn/studios/ZhipuAI/GLM-4.1V-9B-Thinking-Demo" target="_blank">ModelScope</a> 上的 GLM-4.1V-9B-Thinking。
+    <br>
+    📍 在 <a href="https://www.bigmodel.cn/dev/api/visual-reasoning-model/GLM-4.1V-Thinking">智谱大模型开放平台</a> 使用 GLM-4.1V-9B-Thinking 的API服务。
+</p>
+
+## 模型介绍
+
+视觉语言大模型（VLM）已经成为智能系统的关键基石。随着真实世界的智能任务越来越复杂，VLM模型也亟需在基本的多模态感知之外，
+逐渐增强复杂任务中的推理能力，提升自身的准确性、全面性和智能化程度，使得复杂问题解决、长上下文理解、多模态智能体等智能任务成为可能。
+
+基于 [GLM-4-9B-0414](https://github.com/THUDM/GLM-4) 基座模型，我们推出新版VLM开源模型 **GLM-4.1V-9B-Thinking**
+，引入思考范式，通过课程采样强化学习 RLCS（Reinforcement Learning with Curriculum Sampling）全面提升模型能力，
+达到 10B 参数级别的视觉语言模型的最强性能，在18个榜单任务中持平甚至超过8倍参数量的 Qwen-2.5-VL-72B。
+我们同步开源基座模型 **GLM-4.1V-9B-Base**，希望能够帮助更多研究者探索视觉语言模型的能力边界。
+
+![rl](https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/refs/heads/main/resources/rl.jpeg)
+
+与上一代的 CogVLM2 及 GLM-4V 系列模型相比，**GLM-4.1V-Thinking** 有如下改进：
+
+1. 系列中首个推理模型，不仅仅停留在数学领域，在多个子领域均达到世界前列的水平。
+2. 支持 **64k** 上下长度。
+3. 支持**任意长宽比**和高达 **4k** 的图像分辨率。
+4. 提供支持**中英文双语**的开源模型版本。
+
+## 榜单信息
+
+GLM-4.1V-9B-Thinking 通过引入「思维链」（Chain-of-Thought）推理机制，在回答准确性、内容丰富度与可解释性方面，
+全面超越传统的非推理式视觉模型。在28项评测任务中有23项达到10B级别模型最佳，甚至有18项任务超过8倍参数量的Qwen-2.5-VL-72B。
+
+![bench](https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/refs/heads/main/resources/bench.jpeg)
+

chat_template.jinja

@@ -0,0 +1,33 @@
+[gMASK]<sop>
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- elif msg.role == 'user' %}
+<|user|>{{ '\n' }}
+
+        {%- if msg.content is string %}
+{{ msg.content }}
+        {%- else %}
+            {%- for item in msg.content %}
+                {%- if item.type == 'video' or 'video' in item %}
+<|begin_of_video|><|video|><|end_of_video|>
+                {%- elif item.type == 'image' or 'image' in item %}
+<|begin_of_image|><|image|><|end_of_image|>
+                {%- elif item.type == 'text' %}
+{{ item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- elif msg.role == 'assistant' %}
+        {%- if msg.metadata %}
+<|assistant|>{{ msg.metadata }}
+{{ msg.content }}
+        {%- else %}
+<|assistant|>
+{{ msg.content }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>
+{% endif %}

config.json

@@ -0,0 +1,86 @@
+{
+  "name_or_path": "tclf90/GLM-4.1V-9B-Thinking-GPTQ-Int4-Int8Mix",
+  "architectures": [
+    "Glm4vForConditionalGeneration"
+  ],
+  "model_type": "glm4v",
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "pad_token_id": 151329,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338,
+    151348
+  ],
+  "image_start_token_id": 151339,
+  "image_end_token_id": 151340,
+  "video_start_token_id": 151341,
+  "video_end_token_id": 151342,
+  "image_token_id": 151343,
+  "video_token_id": 151344,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 65536,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.53.0dev",
+  "use_cache": true,
+  "vocab_size": 151552,
+  "partial_rotary_factor": 0.5,
+  "vision_config": {
+    "hidden_size": 1536,
+    "depth": 24,
+    "num_heads": 12,
+    "attention_bias": false,
+    "intermediate_size": 13824,
+    "hidden_act": "silu",
+    "hidden_dropout_prob": 0.0,
+    "initializer_range": 0.02,
+    "image_size": 336,
+    "patch_size": 14,
+    "out_hidden_size": 4096,
+    "rms_norm_eps": 1e-05,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "default",
+    "mrope_section": [
+      8,
+      12,
+      12
+    ]
+  },
+  "quantization_config": {
+    "quant_method": "gptq",
+    "bits": 4,
+    "group_size": 128,
+    "sym": false,
+    "desc_act": false,
+    "dynamic": {
+      "+:model.layers\\.([0-4]|3[6-9])\\..*": {
+        "bits": 8
+      },
+      "+:model.layers.*.self_attn.o_proj.*": {
+        "bits": 8
+      },
+      "+:model.layers.*.mlp.down_proj.*": {
+        "bits": 8
+      },
+      "+:visual.blocks.*.attn.proj.*": {
+        "bits": 8
+      },
+      "+:visual.blocks.*.mlp.down_proj.*": {
+        "bits": 8
+      }
+    }
+  }
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d28097498b6874a2291fc59dcf10c942590ae0db9a75076c046a31bea5cccd
+size 4997139480

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7c2e19458408d368dac7c127d23c29e00dd8d7b08c0c9ba5147cb4b767195c
+size 4479333632

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+    "size": {"shortest_edge": 12544, "longest_edge": 9633792},
+    "do_rescale": true,
+    "patch_size": 14,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [0.48145466, 0.4578275, 0.40821073],
+    "image_std": [0.26862954, 0.26130258, 0.27577711],
+    "image_processor_type": "Glm4vImageProcessor",
+    "processor_class": "Glm4vProcessor"
+}

requirements.txt

@@ -0,0 +1,10 @@
+setuptools>=80.9.0
+setuptools_scm>=8.3.1
+git+https://github.com/huggingface/transformers.git@91221da2f1f68df9eb97c980a7206b14c4d3a9b0
+torchvision>=0.22.0
+gradio>=5.35.0
+pre-commit>=4.2.0
+PyMuPDF>=1.26.1
+av>=14.4.0
+accelerate>=1.6.0
+spaces>=0.37.1

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,218 @@
+{
+  "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": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+     "151345": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+     "151346": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+     "151347": {
+      "content": "<answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+     "151348": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151349": {
+      "content": "<|begin_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151350": {
+      "content": "<|end_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151351": {
+      "content": "<|sep|>",
+      "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|>",
+    "<|image|>",
+    "<|video|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 64000,
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}

video_preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+    "size": {"shortest_edge": 12544, "longest_edge": 47040000},
+    "do_rescale": true,
+    "patch_size": 14,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [0.48145466, 0.4578275, 0.40821073],
+    "image_std": [0.26862954, 0.26130258, 0.27577711],
+    "video_processor_type": "Glm4vVideoProcessor",
+    "processor_class": "Glm4vProcessor"
+}