能否提供出一个专门用于做人体行为识别的量化版模型

2026-06-12 04:02:53 +08:00 · 2025-07-02 08:07:32 +00:00
6 changed files with 81 additions and 115 deletions
--- a/.gitattributes
+++ b/.gitattributes
@ -11,7 +11,7 @@
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
- 
+*.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
@ -45,5 +45,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-
-notebook.ipynb filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@ -1,85 +1,67 @@
 ---
 license: mit
-language:
- en
- zh
-base_model:
- zai-org/GLM-4-9B-0414
-pipeline_tag: image-text-to-text
-library_name: transformers
-tags:
- reasoning
 ---

 # GLM-4.1V-9B-Thinking

 <div align="center">
-<img src=https://raw.githubusercontent.com/zai-org/GLM-4.1V-Thinking/99c5eb6563236f0ff43605d91d107544da9863b2/resources/logo.svg width="40%"/>
+<img src=https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/99c5eb6563236f0ff43605d91d107544da9863b2/resources/logo.svg width="40%"/>
 </div>
 <p align="center">
-    📖 View the GLM-4.1V-9B-Thinking <a href="https://arxiv.org/abs/2507.01006" target="_blank">paper</a>.
+    📖 查看 GLM-4.1V-9B-Thinking <a href="https://arxiv.org/abs/2507.01006" target="_blank">论文</a> 。
    <br>
-    📍 Using GLM-4.1V-9B-Thinking API at <a href="https://www.bigmodel.cn/dev/api/visual-reasoning-model/GLM-4.1V-Thinking">Zhipu Foundation Model Open Platform</a>
+    💡 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

-## Model Introduction
+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。

-Vision-Language Models (VLMs) have become foundational components of intelligent systems. As real-world AI tasks grow
-increasingly complex, VLMs must evolve beyond basic multimodal perception to enhance their reasoning capabilities in
-complex tasks. This involves improving accuracy, comprehensiveness, and intelligence, enabling applications such as
-complex problem solving, long-context understanding, and multimodal agents.
+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。

-Based on the [GLM-4-9B-0414](https://github.com/zai-org/GLM-4) foundation model, we present the new open-source VLM model
-**GLM-4.1V-9B-Thinking**, designed to explore the upper limits of reasoning in vision-language models. By introducing
-a "thinking paradigm" and leveraging reinforcement learning, the model significantly enhances its capabilities. It
-achieves state-of-the-art performance among 10B-parameter VLMs, matching or even surpassing the 72B-parameter
-Qwen-2.5-VL-72B on 18 benchmark tasks. We are also open-sourcing the base model GLM-4.1V-9B-Base to
-support further research into the boundaries of VLM capabilities.
+![rl](https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/refs/heads/main/resources/rl.jpeg)

-![rl](https://raw.githubusercontent.com/zai-org/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：

-Compared to the previous generation models CogVLM2 and the GLM-4V series, **GLM-4.1V-Thinking** offers the
-following improvements:
+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。

-1. The first reasoning-focused model in the series, achieving world-leading performance not only in mathematics but also
-   across various sub-domains.
-2. Supports **64k** context length.
-3. Handles **arbitrary aspect ratios** and up to **4K** image resolution.
-4. Provides an open-source version supporting both **Chinese and English bilingual** usage.
+## 榜单信息

-## Benchmark Performance
+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。

-By incorporating the Chain-of-Thought reasoning paradigm, GLM-4.1V-9B-Thinking significantly improves answer accuracy,
-richness, and interpretability. It comprehensively surpasses traditional non-reasoning visual models.
-Out of 28 benchmark tasks, it achieved the best performance among 10B-level models on 23 tasks,
-and even outperformed the 72B-parameter Qwen-2.5-VL-72B on 18 tasks.
+![bench](https://raw.githubusercontent.com/THUDM/GLM-4.1V-Thinking/refs/heads/main/resources/bench.jpeg)

-![bench](https://raw.githubusercontent.com/zai-org/GLM-4.1V-Thinking/refs/heads/main/resources/bench.jpeg)
-
-## Quick Inference
-
-This is a simple example of running single-image inference using the `transformers` library.  
-First, install the `transformers` library from source:
+## 快速推理

+这里展现了一个使用`transformers`进行单张图片推理的代码。首先，从源代码安装`transformers`库。
 ```
-pip install transformers>=4.57.1
+pip install git+https://github.com/huggingface/transformers.git
 ```

-Then, run the following code:
+接着按照以下代码运行:

 ```python
 from transformers import AutoProcessor, Glm4vForConditionalGeneration
 import torch

-MODEL_PATH = "zai-org/GLM-4.1V-9B-Thinking"
+MODEL_PATH = "THUDM/GLM-4.1V-9B-Thinking"
 messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
-                "url": "https://upload.wikimedia.org/wikipedia/commons/f/fa/Grayscale_8bits_palette_sample_image.png"
+                "url": "https://model-demo.oss-cn-hangzhou.aliyuncs.com/Grayscale_8bits_palette_sample_image.png"
            },
            {
                "type": "text",
@ -106,5 +88,6 @@ output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:],
 print(output_text)
 ```

-For video reasoning, web demo deployment, and more code, please check
-our [GitHub](https://github.com/zai-org/GLM-V).
+
+视频推理，网页端Demo部署等更代码请查看我们的 [github](https://github.com/THUDM/GLM-4.1V-Thinking)。
+
--- a/config.json
+++ b/config.json
@ -3,16 +3,6 @@
    "Glm4vForConditionalGeneration"
  ],
  "model_type": "glm4v",
-  "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,
-  "tie_word_embeddings": false,
-  "transformers_version": "4.57.1",
-  "text_config": {
-    "model_type": "glm4v_text",
  "attention_bias": true,
  "attention_dropout": 0.0,
  "pad_token_id": 151329,
@ -22,31 +12,29 @@
    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": 13696,
-    "max_position_embeddings": 65536,
+  "max_position_embeddings": 32768,
  "num_attention_heads": 32,
  "num_hidden_layers": 40,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-05,
-    "dtype": "bfloat16",
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0dev",
  "use_cache": true,
  "vocab_size": 151552,
  "partial_rotary_factor": 0.5,
-    "rope_theta": 10000,
-    "rope_scaling": {
-      "rope_type": "default",
-      "mrope_section": [
-        8,
-        12,
-        12
-      ]
-    }
-  },
  "vision_config": {
-    "model_type": "glm4v",
    "hidden_size": 1536,
    "depth": 24,
    "num_heads": 12,
@ -61,5 +49,13 @@
    "rms_norm_eps": 1e-05,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "default",
+    "mrope_section": [
+      8,
+      12,
+      12
+    ]
  }
 }
--- a/generation_config.json
+++ b/generation_config.json
@ -1,15 +0,0 @@
-{
-  "_from_model_config": true,
-  "do_sample": true,
-  "eos_token_id": [
-    151329,
-    151336,
-    151338,
-    151348
-  ],
-  "pad_token_id": 151329,
-  "top_p": 0.6,
-  "temperature": 0.8,
-  "top_k": 2,
-  "transformers_version": "4.57.1"
-}
--- a/notebook.ipynb
+++ b/notebook.ipynb
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@ -134,7 +134,7 @@
      "normalized": false,
      "rstrip": false,
      "single_word": false,
-      "special": false
+      "special": true
    },
     "151346": {
      "content": "</think>",
@ -142,7 +142,7 @@
      "normalized": false,
      "rstrip": false,
      "single_word": false,
-      "special": false
+      "special": true
    },
     "151347": {
      "content": "<answer>",
@ -150,7 +150,7 @@
      "normalized": false,
      "rstrip": false,
      "single_word": false,
-      "special": false
+      "special": true
    },
     "151348": {
      "content": "</answer>",
@ -158,7 +158,7 @@
      "normalized": false,
      "rstrip": false,
      "single_word": false,
-      "special": false
+      "special": true
    },
    "151349": {
      "content": "<|begin_of_box|>",
@ -166,7 +166,7 @@
      "normalized": false,
      "rstrip": false,
      "single_word": false,
-      "special": false
+      "special": true
    },
    "151350": {
      "content": "<|end_of_box|>",
@ -174,7 +174,7 @@
      "normalized": false,
      "rstrip": false,
      "single_word": false,
-      "special": false
+      "special": true
    },
    "151351": {
      "content": "<|sep|>",
@ -182,7 +182,7 @@
      "normalized": false,
      "rstrip": false,
      "single_word": false,
-      "special": false
+      "special": true
    }
  },
  "additional_special_tokens": [
@ -200,8 +200,15 @@
    "<|end_of_image|>",
    "<|begin_of_video|>",
    "<|end_of_video|>",
+    "<|begin_of_box|>",
+    "<|end_of_box|>",
+    "<|sep|>",
    "<|image|>",
-    "<|video|>"
+    "<|video|>",
+    "<think>",
+    "</think>",
+    "<answer>",
+    "</answer>"
  ],
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
@ -211,7 +218,7 @@
    "input_ids",
    "attention_mask"
  ],
-  "model_max_length": 65536,
+  "model_max_length": 64000,
  "padding_side": "left",
  "remove_space": false,
  "tokenizer_class": "PreTrainedTokenizer"