first commit
This commit is contained in:
xxl
parent
2f4e0e9e6b
commit
46dd9b2531
198
README.md
198
README.md
|
|
@ -1,3 +1,197 @@
|
|||
# UI-TARS-7B-DPO
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: image-text-to-text
|
||||
tags:
|
||||
- multimodal
|
||||
- gui
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
UI-TARS-7B-DPO
|
||||
|
||||
# UI-TARS-7B-DPO
|
||||
[UI-TARS-2B-SFT](https://huggingface.co/bytedance-research/UI-TARS-2B-SFT) |
|
||||
[UI-TARS-7B-SFT](https://huggingface.co/bytedance-research/UI-TARS-7B-SFT) |
|
||||
[**UI-TARS-7B-DPO**](https://huggingface.co/bytedance-research/UI-TARS-7B-DPO)(Recommended) |
|
||||
[UI-TARS-72B-SFT](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT) |
|
||||
[**UI-TARS-72B-DPO**](https://huggingface.co/bytedance-research/UI-TARS-72B-DPO)(Recommended)
|
||||
## Introduction
|
||||
|
||||
UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities. Unlike traditional modular frameworks, UI-TARS integrates all key components—perception, reasoning, grounding, and memory—within a single vision-language model (VLM), enabling end-to-end task automation without predefined workflows or manual rules.
|
||||
<!--  -->
|
||||
<p align="center">
|
||||
<img src="https://github.com/bytedance/UI-TARS/blob/main/figures/UI-TARS-vs-Previous-SOTA.png?raw=true" width="90%"/>
|
||||
<p>
|
||||
<p align="center">
|
||||
<img src="https://github.com/bytedance/UI-TARS/blob/main/figures/UI-TARS.png?raw=true" width="90%"/>
|
||||
<p>
|
||||
|
||||
<!--  -->
|
||||
|
||||
This repository contains the model for the paper [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://huggingface.co/papers/2501.12326).
|
||||
|
||||
Code: https://github.com/bytedance/UI-TARS
|
||||
|
||||
## Performance
|
||||
**Perception Capabilty Evaluation**
|
||||
| Model | VisualWebBench | WebSRC | SQAshort |
|
||||
|---------------------------|---------------|---------|----------|
|
||||
| Qwen2-VL-7B | 73.3 | 81.8 | 84.9 |
|
||||
| Qwen-VL-Max | 74.1 | 91.1 | 78.6 |
|
||||
| Gemini-1.5-Pro | 75.4 | 88.9 | 82.2 |
|
||||
| UIX-Qwen2-7B | 75.9 | 82.9 | 78.8 |
|
||||
| Claude-3.5-Sonnet | 78.2 | 90.4 | 83.1 |
|
||||
| GPT-4o | 78.5 | 87.7 | 82.3 |
|
||||
| **UI-TARS-2B** | 72.9 | 89.2 | 86.4 |
|
||||
| **UI-TARS-7B** | 79.7 | **93.6** | 87.7 |
|
||||
| **UI-TARS-72B** | **82.8** | 89.3 | **88.6** |
|
||||
|
||||
**Grounding Capability Evaluation**
|
||||
- **ScreenSpot Pro**
|
||||
|
||||
| Agent Model | Dev-Text | Dev-Icon | Dev-Avg | Creative-Text | Creative-Icon | Creative-Avg | CAD-Text | CAD-Icon | CAD-Avg | Scientific-Text | Scientific-Icon | Scientific-Avg | Office-Text | Office-Icon | Office-Avg | OS-Text | OS-Icon | OS-Avg | Avg-Text | Avg-Icon | Avg |
|
||||
|--------------------------|----------|----------|----------|--------------|--------------|--------------|---------|---------|---------|---------------|---------------|---------------|------------|------------|------------|--------|--------|--------|---------|---------|------|
|
||||
| QwenVL-7B | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.7 | 0.0 | 0.4 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1 | 0.0 | **0.1** |
|
||||
| GPT-4o | 1.3 | 0.0 | 0.7 | 1.0 | 0.0 | 0.6 | 2.0 | 0.0 | 1.5 | 2.1 | 0.0 | 1.2 | 1.1 | 0.0 | 0.9 | 0.0 | 0.0 | 0.0 | 1.3 | 0.0 | **0.8** |
|
||||
| SeeClick | 0.6 | 0.0 | 0.3 | 1.0 | 0.0 | 0.6 | 2.5 | 0.0 | 1.9 | 3.5 | 0.0 | 2.0 | 1.1 | 0.0 | 0.9 | 2.8 | 0.0 | 1.5 | 1.8 | 0.0 | **1.1** |
|
||||
| Qwen2-VL-7B | 2.6 | 0.0 | 1.3 | 1.5 | 0.0 | 0.9 | 0.5 | 0.0 | 0.4 | 6.3 | 0.0 | 3.5 | 3.4 | 1.9 | 3.0 | 0.9 | 0.0 | 0.5 | 2.5 | 0.2 | **1.6** |
|
||||
| OS-Atlas-4B | 7.1 | 0.0 | 3.7 | 3.0 | 1.4 | 2.3 | 2.0 | 0.0 | 1.5 | 9.0 | 5.5 | 7.5 | 5.1 | 3.8 | 4.8 | 5.6 | 0.0 | 3.1 | 5.0 | 1.7 | **3.7** |
|
||||
| ShowUI-2B | 16.9 | 1.4 | 9.4 | 9.1 | 0.0 | 5.3 | 2.5 | 0.0 | 1.9 | 13.2 | 7.3 | 10.6 | 15.3 | 7.5 | 13.5 | 10.3 | 2.2 | 6.6 | 10.8 | 2.6 | **7.7** |
|
||||
| CogAgent-18B | 14.9 | 0.7 | 8.0 | 9.6 | 0.0 | 5.6 | 7.1 | 3.1 | 6.1 | 22.2 | 1.8 | 13.4 | 13.0 | 0.0 | 10.0 | 5.6 | 0.0 | 3.1 | 12.0 | 0.8 | **7.7** |
|
||||
| Aria-UI | 16.2 | 0.0 | 8.4 | 23.7 | 2.1 | 14.7 | 7.6 | 1.6 | 6.1 | 27.1 | 6.4 | 18.1 | 20.3 | 1.9 | 16.1 | 4.7 | 0.0 | 2.6 | 17.1 | 2.0 | **11.3** |
|
||||
| UGround-7B | 26.6 | 2.1 | 14.7 | 27.3 | 2.8 | 17.0 | 14.2 | 1.6 | 11.1 | 31.9 | 2.7 | 19.3 | 31.6 | 11.3 | 27.0 | 17.8 | 0.0 | 9.7 | 25.0 | 2.8 | **16.5** |
|
||||
| Claude Computer Use | 22.0 | 3.9 | 12.6 | 25.9 | 3.4 | 16.8 | 14.5 | 3.7 | 11.9 | 33.9 | 15.8 | 25.8 | 30.1 | 16.3 | 26.9 | 11.0 | 4.5 | 8.1 | 23.4 | 7.1 | **17.1** |
|
||||
| OS-Atlas-7B | 33.1 | 1.4 | 17.7 | 28.8 | 2.8 | 17.9 | 12.2 | 4.7 | 10.3 | 37.5 | 7.3 | 24.4 | 33.9 | 5.7 | 27.4 | 27.1 | 4.5 | 16.8 | 28.1 | 4.0 | **18.9** |
|
||||
| UGround-V1-7B | - | - | 35.5 | - | - | 27.8 | - | - | 13.5 | - | - | 38.8 | - | - | 48.8 | - | - | 26.1 | - | - | **31.1** |
|
||||
| **UI-TARS-2B** | 47.4 | 4.1 | 26.4 | 42.9 | 6.3 | 27.6 | 17.8 | 4.7 | 14.6 | 56.9 | 17.3 | 39.8 | 50.3 | 17.0 | 42.6 | 21.5 | 5.6 | 14.3 | 39.6 | 8.4 | **27.7** |
|
||||
| **UI-TARS-7B** | 58.4 | 12.4 | 36.1 | 50.0 | 9.1 | 32.8 | **20.8**| 9.4 | **18.0**| 63.9 | **31.8** | **50.0** | **63.3** | 20.8 | 53.5 | 30.8 | **16.9**| 24.5 | 47.8 | 16.2 | **35.7** |
|
||||
| **UI-TARS-72B** | **63.0** | **17.3** | **40.8** | **57.1** | **15.4** | **39.6** | 18.8 | **12.5**| 17.2 | **64.6** | 20.9 | 45.7 | **63.3** | **26.4** | **54.8** | **42.1**| 15.7 | **30.1**| **50.9**| **17.5**| **38.1** |
|
||||
|
||||
|
||||
- **ScreenSpot**
|
||||
|
||||
| Method | Mobile-Text | Mobile-Icon/Widget | Desktop-Text | Desktop-Icon/Widget | Web-Text | Web-Icon/Widget | Avg |
|
||||
|--------|-------------|-------------|-------------|-------------|-------------|---------|---------|
|
||||
| **Agent Framework** | | | | | | | |
|
||||
| GPT-4 (SeeClick) | 76.6 | 55.5 | 68.0 | 28.6 | 40.9 | 23.3 | **48.8** |
|
||||
| GPT-4 (OmniParser) | 93.9 | 57.0 | 91.3 | 63.6 | 81.3 | 51.0 | **73.0** |
|
||||
| GPT-4 (UGround-7B) | 90.1 | 70.3 | 87.1 | 55.7 | 85.7 | 64.6 | **75.6** |
|
||||
| GPT-4o (SeeClick) | 81.0 | 59.8 | 69.6 | 33.6 | 43.9 | 26.2 | **52.3** |
|
||||
| GPT-4o (UGround-7B) | 93.4 | 76.9 | 92.8 | 67.9 | 88.7 | 68.9 | **81.4** |
|
||||
| **Agent Model** | | | | | | | |
|
||||
| GPT-4 | 22.6 | 24.5 | 20.2 | 11.8 | 9.2 | 8.8 | **16.2** |
|
||||
| GPT-4o | 20.2 | 24.9 | 21.1 | 23.6 | 12.2 | 7.8 | **18.3** |
|
||||
| CogAgent | 67.0 | 24.0 | 74.2 | 20.0 | 70.4 | 28.6 | **47.4** |
|
||||
| SeeClick | 78.0 | 52.0 | 72.2 | 30.0 | 55.7 | 32.5 | **53.4** |
|
||||
| Qwen2-VL | 75.5 | 60.7 | 76.3 | 54.3 | 35.2 | 25.7 | **55.3** |
|
||||
| UGround-7B | 82.8 | 60.3 | 82.5 | 63.6 | 80.4 | 70.4 | **73.3** |
|
||||
| Aguvis-G-7B | 88.3 | 78.2 | 88.1 | 70.7 | 85.7 | 74.8 | **81.8** |
|
||||
| OS-Atlas-7B | 93.0 | 72.9 | 91.8 | 62.9 | 90.9 | 74.3 | **82.5** |
|
||||
| Claude Computer Use | - | - | - | - | - | - | **83.0** |
|
||||
| Gemini 2.0 (Project Mariner) | - | - | - | - | - | - | **84.0** |
|
||||
| Aguvis-7B | **95.6** | 77.7 | 93.8 | 67.1 | 88.3 | 75.2 | **84.4** |
|
||||
| Aguvis-72B | 94.5 | **85.2** | 95.4 | 77.9 | **91.3** | **85.9** | **89.2** |
|
||||
| **Our Model** | | | | | | | |
|
||||
| **UI-TARS-2B** | 93.0 | 75.5 | 90.7 | 68.6 | 84.3 | 74.8 | **82.3** |
|
||||
| **UI-TARS-7B** | 94.5 | **85.2** | **95.9** | 85.7 | 90.0 | 83.5 | **89.5** |
|
||||
| **UI-TARS-72B** | 94.9 | 82.5 | 89.7 | **88.6** | 88.7 | 85.0 | **88.4** |
|
||||
|
||||
|
||||
- **ScreenSpot v2**
|
||||
|
||||
| Method | Mobile-Text | Mobile-Icon/Widget | Desktop-Text | Desktop-Icon/Widget | Web-Text | Web-Icon/Widget | Avg |
|
||||
|--------|-------------|-------------|-------------|-------------|-------------|---------|---------|
|
||||
| **Agent Framework** | | | | | | | |
|
||||
| GPT-4o (SeeClick) | 85.2 | 58.8 | 79.9 | 37.1 | 72.7 | 30.1 | **63.6** |
|
||||
| GPT-4o (OS-Atlas-4B) | 95.5 | 75.8 | 79.4 | 49.3 | 90.2 | 66.5 | **79.1** |
|
||||
| GPT-4o (OS-Atlas-7B) | 96.2 | 83.4 | 89.7 | 69.3 | **94.0** | 79.8 | **87.1** |
|
||||
| **Agent Model** | | | | | | | |
|
||||
| SeeClick | 78.4 | 50.7 | 70.1 | 29.3 | 55.2 | 32.5 | **55.1** |
|
||||
| OS-Atlas-4B | 87.2 | 59.7 | 72.7 | 46.4 | 85.9 | 63.1 | **71.9** |
|
||||
| OS-Atlas-7B | 95.2 | 75.8 | 90.7 | 63.6 | 90.6 | 77.3 | **84.1** |
|
||||
| **Our Model** | | | | | | | |
|
||||
| **UI-TARS-2B** | 95.2 | 79.1 | 90.7 | 68.6 | 87.2 | 78.3 | **84.7** |
|
||||
| **UI-TARS-7B** | **96.9** | **89.1** | **95.4** | 85.0 | 93.6 | 85.2 | **91.6** |
|
||||
| **UI-TARS-72B** | 94.8 | 86.3 | 91.2 | **87.9** | 91.5 | **87.7** | **90.3** |
|
||||
|
||||
|
||||
**Offline Agent Capability Evaluation**
|
||||
- **Multimodal Mind2Web**
|
||||
|
||||
| Method | Cross-Task Ele.Acc | Cross-Task Op.F1 | Cross-Task Step SR | Cross-Website Ele.Acc | Cross-Website Op.F1 | Cross-Website Step SR | Cross-Domain Ele.Acc | Cross-Domain Op.F1 | Cross-Domain Step SR |
|
||||
|--------|----------------------|-------------------|--------------------|----------------------|--------------------|-------------------|--------------------|-------------------|-------------------|
|
||||
| **Agent Framework** | | | | | | | | | |
|
||||
| GPT-4o (SeeClick) | 32.1 | - | - | 33.1 | - | - | 33.5 | - | - |
|
||||
| GPT-4o (UGround) | 47.7 | - | - | 46.0 | - | - | 46.6 | - | - |
|
||||
| GPT-4o (Aria-UI) | 57.6 | - | - | 57.7 | - | - | 61.4 | - | - |
|
||||
| GPT-4V (OmniParser) | 42.4 | 87.6 | 39.4 | 41.0 | 84.8 | 36.5 | 45.5 | 85.7 | 42.0 |
|
||||
| **Agent Model** | | | | | | | | | |
|
||||
| GPT-4o | 5.7 | 77.2 | 4.3 | 5.7 | 79.0 | 3.9 | 5.5 | 86.4 | 4.5 |
|
||||
| GPT-4 (SOM) | 29.6 | - | 20.3 | 20.1 | - | 13.9 | 27.0 | - | 23.7 |
|
||||
| GPT-3.5 (Text-only) | 19.4 | 59.2 | 16.8 | 14.9 | 56.5 | 14.1 | 25.2 | 57.9 | 24.1 |
|
||||
| GPT-4 (Text-only) | 40.8 | 63.1 | 32.3 | 30.2 | 61.0 | 27.0 | 35.4 | 61.9 | 29.7 |
|
||||
| Claude | 62.7 | 84.7 | 53.5 | 59.5 | 79.6 | 47.7 | 64.5 | 85.4 | 56.4 |
|
||||
| Aguvis-7B | 64.2 | 89.8 | 60.4 | 60.7 | 88.1 | 54.6 | 60.4 | 89.2 | 56.6 |
|
||||
| CogAgent | - | - | 62.3 | - | - | 54.0 | - | - | 59.4 |
|
||||
| Aguvis-72B | 69.5 | 90.8 | 64.0 | 62.6 | 88.6 | 56.5 | 63.5 | 88.5 | 58.2 |
|
||||
| **Our Model** | | | | | | | | | |
|
||||
| **UI-TARS-2B** | 62.3 | 90.0 | 56.3 | 58.5 | 87.2 | 50.8 | 58.8 | 89.6 | 52.3 |
|
||||
| **UI-TARS-7B** | 73.1 | 92.2 | 67.1 | 68.2 | 90.9 | 61.7 | 66.6 | 90.9 | 60.5 |
|
||||
| **UI-TARS-72B** | **74.7** | **92.5** | **68.6** | **72.4** | **91.2** | **63.5** | **68.9** | **91.8** | **62.1** |
|
||||
|
||||
|
||||
- **Android Control and GUI Odyssey**
|
||||
|
||||
| Agent Models | AndroidControl-Low Type | AndroidControl-Low Grounding | AndroidControl-Low SR | AndroidControl-High Type | AndroidControl-High Grounding | AndroidControl-High SR | GUIOdyssey Type | GUIOdyssey Grounding | GUIOdyssey SR |
|
||||
|---------------------|----------------------|----------------------|----------------|----------------------|----------------------|----------------|----------------|----------------|----------------|
|
||||
| Claude | 74.3 | 0.0 | 19.4 | 63.7 | 0.0 | 12.5 | 60.9 | 0.0 | 3.1 |
|
||||
| GPT-4o | 74.3 | 0.0 | 19.4 | 66.3 | 0.0 | 20.8 | 34.3 | 0.0 | 3.3 |
|
||||
| SeeClick | 93.0 | 73.4 | 75.0 | 82.9 | 62.9 | 59.1 | 71.0 | 52.4 | 53.9 |
|
||||
| InternVL-2-4B | 90.9 | 84.1 | 80.1 | 84.1 | 72.7 | 66.7 | 82.1 | 55.5 | 51.5 |
|
||||
| Qwen2-VL-7B | 91.9 | 86.5 | 82.6 | 83.8 | 77.7 | 69.7 | 83.5 | 65.9 | 60.2 |
|
||||
| Aria-UI | -- | 87.7 | 67.3 | -- | 43.2 | 10.2 | -- | 86.8 | 36.5 |
|
||||
| OS-Atlas-4B | 91.9 | 83.8 | 80.6 | 84.7 | 73.8 | 67.5 | 83.5 | 61.4 | 56.4 |
|
||||
| OS-Atlas-7B | 93.6 | 88.0 | 85.2 | 85.2 | 78.5 | 71.2 | 84.5 | 67.8 | 62.0 |
|
||||
| Aguvis-7B | -- | -- | 80.5 | -- | -- | 61.5 | -- | -- | -- |
|
||||
| Aguvis-72B | -- | -- | 84.4 | -- | -- | 66.4 | -- | -- | -- |
|
||||
| **UI-TARS-2B** | **98.1** | 87.3 | 89.3 | 81.2 | 78.4 | 68.9 | 93.9 | 86.8 | 83.4 |
|
||||
| **UI-TARS-7B** | 98.0 | 89.3 | 90.8 | 83.7 | 80.5 | 72.5 | 94.6 | 90.1 | 87.0 |
|
||||
| **UI-TARS-72B** | **98.1** | **89.9** | **91.3** | **85.2** | **81.5** | **74.7** | **95.4** | **91.4** | **88.6** |
|
||||
|
||||
**Online Agent Capability Evaluation**
|
||||
|
||||
| Method | OSWorld (Online) | AndroidWorld (Online) |
|
||||
|--------|-------------------|------------------|
|
||||
| **Agent Framework** | | |
|
||||
| GPT-4o (UGround) | - | 32.8 |
|
||||
| GPT-4o (Aria-UI) | 15.2 | 44.8 |
|
||||
| GPT-4o (Aguvis-7B) | 14.8 | 37.1 |
|
||||
| GPT-4o (Aguvis-72B) | 17.0 | - |
|
||||
| GPT-4o (OS-Atlas-7B) | 14.6 | - |
|
||||
| **Agent Model** | | |
|
||||
| GPT-4o | 5.0 | 34.5 (SoM) |
|
||||
| Gemini-Pro-1.5 | 5.4 | 22.8 (SoM) |
|
||||
| Aguvis-72B | 10.3 | 26.1 |
|
||||
| Claude Computer-Use | 14.9 (15 steps) | 27.9 |
|
||||
| Claude Computer-Use | 22.0 (50 steps) | - |
|
||||
| **Our Model** | | |
|
||||
| **UI-TARS-7B-SFT** | 17.7 (15 steps) | 33.0 |
|
||||
| **UI-TARS-7B-DPO** | 18.7 (15 steps) | - |
|
||||
| **UI-TARS-72B-SFT** | 18.8 (15 steps) | **46.6** |
|
||||
| **UI-TARS-72B-DPO** | **22.7** (15 steps) | - |
|
||||
| **UI-TARS-72B-DPO** | **24.6** (50 steps) | - |
|
||||
|
||||
|
||||
## Citation
|
||||
If you find our paper and model useful in your research, feel free to give us a cite.
|
||||
|
||||
```BibTeX
|
||||
@article{uitars2025,
|
||||
author = {Yujia Qin, Yining Ye, Junjie Fang, Haoming Wang, Shihao Liang, Shizuo Tian, Junda Zhang, Jiahao Li, Yunxin Li, Shijue Huang, Wanjun Zhong, Kuanye Li, Jiale Yang, Yu Miao, Woyu Lin, Longxiang Liu, Xu Jiang, Qianli Ma, Jingyu Li, Xiaojun Xiao, Kai Cai, Chuang Li, Yaowei Zheng, Chaolin Jin, Chen Li, Xiao Zhou, Minchao Wang, Haoli Chen, Zhaojian Li, Haihua Yang, Haifeng Liu, Feng Lin, Tao Peng, Xin Liu, Guang Shi},
|
||||
title = {UI-TARS: Pioneering Automated GUI Interaction with Native Agents},
|
||||
journal = {arXiv preprint arXiv:2501.12326},
|
||||
url = {https://github.com/bytedance/UI-TARS},
|
||||
year = {2025}
|
||||
}
|
||||
```
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
{
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
{
|
||||
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||
}
|
||||
|
|
@ -0,0 +1,46 @@
|
|||
{
|
||||
"architectures": [
|
||||
"Qwen2VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_vl",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.47.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"in_chans": 3,
|
||||
"model_type": "qwen2_vl",
|
||||
"spatial_patch_size": 14
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"transformers_version": "4.47.1"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,737 @@
|
|||
{
|
||||
"metadata": {
|
||||
"total_size": 16582751232
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.ln_q.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,29 @@
|
|||
{
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"max_pixels": 2116800,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"max_pixels": 2116800,
|
||||
"min_pixels": 3136
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,145 @@
|
|||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{ message['role'].title() + ': ' + message['content'] | trim + eos_token + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"processor_class": "Qwen2VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue