fgegdff FireRedTeam commited on
Commit
ecb2fe4
·
0 Parent(s):

Duplicate from FireRedTeam/FireRed-Image-Edit-1.0

Browse files

Co-authored-by: FireRedTeam <FireRedTeam@users.noreply.huggingface.co>

Files changed (39) hide show
  1. .gitattributes +15 -0
  2. README.md +812 -0
  3. assets/architecture.png +3 -0
  4. assets/logo.png +3 -0
  5. assets/showcase.png +3 -0
  6. assets/teaser.png +3 -0
  7. model_index.json +28 -0
  8. processor/added_tokens.json +24 -0
  9. processor/chat_template.jinja +7 -0
  10. processor/merges.txt +0 -0
  11. processor/preprocessor_config.json +39 -0
  12. processor/special_tokens_map.json +31 -0
  13. processor/tokenizer.json +3 -0
  14. processor/tokenizer_config.json +208 -0
  15. processor/video_preprocessor_config.json +45 -0
  16. processor/vocab.json +0 -0
  17. scheduler/scheduler_config.json +18 -0
  18. text_encoder/config.json +131 -0
  19. text_encoder/generation_config.json +14 -0
  20. text_encoder/model-00001-of-00004.safetensors +3 -0
  21. text_encoder/model-00002-of-00004.safetensors +3 -0
  22. text_encoder/model-00003-of-00004.safetensors +3 -0
  23. text_encoder/model-00004-of-00004.safetensors +3 -0
  24. text_encoder/model.safetensors.index.json +737 -0
  25. tokenizer/added_tokens.json +24 -0
  26. tokenizer/chat_template.jinja +54 -0
  27. tokenizer/merges.txt +0 -0
  28. tokenizer/special_tokens_map.json +31 -0
  29. tokenizer/tokenizer_config.json +207 -0
  30. tokenizer/vocab.json +0 -0
  31. transformer/config.json +17 -0
  32. transformer/diffusion_pytorch_model-00001-of-00005.safetensors +3 -0
  33. transformer/diffusion_pytorch_model-00002-of-00005.safetensors +3 -0
  34. transformer/diffusion_pytorch_model-00003-of-00005.safetensors +3 -0
  35. transformer/diffusion_pytorch_model-00004-of-00005.safetensors +3 -0
  36. transformer/diffusion_pytorch_model-00005-of-00005.safetensors +3 -0
  37. transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
  38. vae/config.json +56 -0
  39. vae/diffusion_pytorch_model.safetensors +3 -0
.gitattributes ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2
+ text_encoder/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
3
+ text_encoder/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
4
+ text_encoder/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
5
+ text_encoder/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
6
+ transformer/diffusion_pytorch_model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
7
+ transformer/diffusion_pytorch_model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
8
+ transformer/diffusion_pytorch_model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
9
+ transformer/diffusion_pytorch_model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
10
+ transformer/diffusion_pytorch_model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
11
+ vae/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
12
+ assets/logo.png filter=lfs diff=lfs merge=lfs -text
13
+ assets/architecture.png filter=lfs diff=lfs merge=lfs -text
14
+ assets/showcase.png filter=lfs diff=lfs merge=lfs -text
15
+ assets/teaser.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,812 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - zh
6
+ ---
7
+ <p align="center">
8
+ <img src="./assets/logo.png" width="600"/>
9
+ <p>
10
+ <p align="center" style="line-height: 1;">
11
+ <a href="https://huggingface.co/FireRedTeam" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-FireRedTeam-ffc107?color=ffc107&logoColor=white" style="display: inline-block;"/></a>
12
+ <a href="https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.0" target="_blank"><img alt="Hugging Face Model" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-FireRed--Image--Edit--1.0-red" style="display: inline-block;"/></a>
13
+ <a href="https://huggingface.co/spaces/FireRedTeam/FireRed-Image-Edit-1.0" target="_blank"><img alt="Demo" src="https://img.shields.io/badge/%F0%9F%92%BB%20Demo-FireRed--Image--Edit--1.0-red" style="display: inline-block;"/></a>
14
+ </p>
15
+
16
+ <p align="center" style="line-height: 1;">
17
+ 🤗 <a href="https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.0">HuggingFace</a> |
18
+ 🖥️ <a href="https://huggingface.co/spaces/FireRedTeam/FireRed-Image-Edit-1.0"> Demo</a> |
19
+ 📄 <a href="https://github.com/FireRedTeam/FireRed-Image-Edit/blob/main/assets/FireRed_Image_Edit_1_0_Techinical_Report.pdf">Technical Report</a>
20
+ </p>
21
+ <p align="center">
22
+ <img src="./assets/teaser.png" width="800"/>
23
+ <p>
24
+
25
+
26
+ ## 🔥 FireRed-Image-Edit
27
+ **FireRed-Image-Edit** is a general-purpose image editing model that delivers high-fidelity and consistent editing across a wide range of scenarios.
28
+
29
+ ## ✨ Key Features
30
+ - **Strong Editing Performance**: FireRed-Image-Edit delivers leading open-source results with accurate instruction following, high image quality, and consistent visual coherence.
31
+ - **Native Editing Capability**: Built directly from text-to-image foundation model and endowed with editing capabilities.
32
+ - **Text Style Preservation**: Maintains text styles with high fidelity, achieving performance comparable to closed-source solutions.
33
+ - **Photo Restoration**: High-quality old photo restoration and enhancement.
34
+ - **Multi-Image Editing**: Flexible editing of multiple images such as virtual try-on.
35
+
36
+
37
+ ## 📰 News
38
+ - 2026.02.14: We released FireRed-Image-Edit-1.0 model weights. Check more details in the [Model Zoo](#-model-zoo) section.
39
+ - 2026.02.10: We released the [Technical Report](https://github.com/FireRedTeam/FireRed-Image-Edit/blob/main/assets/FireRed_Image_Edit_1_0_Techinical_Report.pdf) of FireRed-Image-Edit-1.0.
40
+
41
+ ## 🎨 Showcase
42
+ Some real outputs produced by FireRed-Image-Edit across genearl editing.
43
+ <p align="center">
44
+ <img src="./assets/showcase.png" width="800"/>
45
+ <p>
46
+
47
+ ## 🗂️ Model Zoo
48
+
49
+ <div style="overflow-x: auto; margin-bottom: 16px;">
50
+ <table style="border-collapse: collapse; width: 100%;">
51
+ <thead>
52
+ <tr>
53
+ <th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Models</th>
54
+ <th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Task</th>
55
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Description</th>
56
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Download Link</th>
57
+ </tr>
58
+ </thead>
59
+ <tbody>
60
+ <tr>
61
+ <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">FireRed-Image-Edit-1.0</td>
62
+ <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Image-Editing</td>
63
+ <td style="padding: 8px; border: 1px solid #d0d7de;">General-purpose image editing model</td>
64
+ <td style="padding: 8px; border: 1px solid #d0d7de;">
65
+ <span style="white-space: nowrap;">🤗&nbsp;<a href="https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.0">HuggingFace</a></span>
66
+ </td>
67
+ </tr>
68
+ <tr>
69
+ <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">FireRed-Image-Edit-1.0-Distilled</td>
70
+ <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Image-Editing</td>
71
+ <td style="padding: 8px; border: 1px solid #d0d7de;">Distilled version of FireRed-Image-Edit-1.0 for faster inference</td>
72
+ <td style="padding: 8px; border: 1px solid #d0d7de;">
73
+ <span style="white-space: nowrap;">To be released</span>
74
+ </td>
75
+ </tr>
76
+ <tr>
77
+ <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">FireRed-Image</td>
78
+ <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Text-to-Image</td>
79
+ <td style="padding: 8px; border: 1px solid #d0d7de;">High-quality text-to-image generation model</td>
80
+ <td style="padding: 8px; border: 1px solid #d0d7de;">
81
+ <span style="white-space: nowrap;">To be released</span>
82
+ </td>
83
+ </tr>
84
+ </tbody>
85
+ </table>
86
+ </div>
87
+
88
+ ## 🏗️ Model Architecture
89
+ <p align="center">
90
+ <img src="./assets/architecture.png" width="800"/>
91
+ <p>
92
+
93
+ ## ⚡️ Quick Start
94
+
95
+ 1. Install the latest version of diffusers
96
+ ```
97
+ pip install git+https://github.com/huggingface/diffusers
98
+ ```
99
+ 2. Use the following code snippets to generate or edit images.
100
+ ```
101
+ python inference.py \
102
+ --input_image ./examples/edit_example.png \
103
+ --prompt "在书本封面Python的下方,添加一行英文文字2nd Edition" \
104
+ --output_image output_edit.png \
105
+ --seed 43
106
+ ```
107
+
108
+ ## 📊 Benchmark
109
+ To better validate the capabilities of our model, we propose a benchmark called REDEdit-Bench. Our main goal is to build more diverse scenarios and editing instructions that better align with human language, enabling a more comprehensive evaluation of current editing models. We collected over 3,000 images from the internet, and after careful expert-designed selection, we constructed 1,673 bilingual (Chinese–English) editing pairs across 15 categories.
110
+
111
+ ### Inference and Evaluation Code
112
+ We provide the inference and evaluation code for REDEdit-Bench. Please refer to the [redbench_infer.py](./src/tools/redbench_infer.py) and [redbench_eval.py](./src/tools/redbench_eval.py) scripts in the `src/tools` directory for more details.
113
+
114
+ ### Benchmark Distribution
115
+ The REDEdit-Bench dataset will be available soon.
116
+
117
+ ### Results on ImgEdit
118
+
119
+ <table style="border-collapse:collapse; width:100%; font-family:system-ui, -apple-system, Segoe UI, Roboto, Arial, sans-serif; font-size:14px;">
120
+ <thead>
121
+ <tr>
122
+ <th style="border:1px solid #ddd; padding:8px; text-align:left;">Model</th>
123
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Overall ↑</th>
124
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Add</th>
125
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Adjust</th>
126
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Extract</th>
127
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Replace</th>
128
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Remove</th>
129
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">BG</th>
130
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Style</th>
131
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Hybrid</th>
132
+ <th style="border:1px solid #ddd; padding:8px; text-align:center;">Action</th>
133
+ </tr>
134
+ </thead>
135
+ <tbody><tr>
136
+ <td colspan="11" style="border:1px solid #ddd; padding:8px; font-weight:700; background:#f7f7f7;">
137
+ 🔹 Proprietary Models
138
+ </td>
139
+ </tr><tr>
140
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">Nano-Banana</td>
141
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.29</td>
142
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.62</b></td>
143
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.41</td>
144
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>3.68</u></td>
145
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.34</td>
146
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.39</td>
147
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.40</b></td>
148
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.18</td>
149
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>3.72</b></td>
150
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.83</b></td>
151
+ </tr><tr>
152
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">Seedream4.0</td>
153
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.30</td>
154
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.33</td>
155
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.38</td>
156
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>3.89</b></td>
157
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.65</u></td>
158
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.57</u></td>
159
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.35</td>
160
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.22</td>
161
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>3.71</u></td>
162
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.61</td>
163
+ </tr><tr>
164
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">Seedream4.5</td>
165
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.32</u></td>
166
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.57</u></td>
167
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.65</b></td>
168
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">2.97</td>
169
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.66</b></td>
170
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.46</td>
171
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.37</u></td>
172
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.92</u></td>
173
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>3.71</u></td>
174
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.56</td>
175
+ </tr><tr>
176
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">Nano-Banana-Pro</td>
177
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.37</b></td>
178
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.44</td>
179
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.62</u></td>
180
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.42</td>
181
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.60</td>
182
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.63</b></td>
183
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.32</td>
184
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.97</b></td>
185
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.64</td>
186
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.69</u></td>
187
+ </tr><tr>
188
+ <td colspan="11" style="border:1px solid #ddd; padding:8px; font-weight:700; background:#f7f7f7;" >
189
+ 🔹 Open-source Models
190
+ </td>
191
+ </tr><tr>
192
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">FLUX.1 Kontext [Dev]</td>
193
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.71</td>
194
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.99</td>
195
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.88</td>
196
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">2.19</td>
197
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.27</td>
198
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.13</td>
199
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.98</td>
200
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.51</td>
201
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.23</td>
202
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.18</td>
203
+ </tr><tr>
204
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">Step1X-Edit-v1.2</td>
205
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.95</td>
206
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.91</td>
207
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.04</td>
208
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">2.68</td>
209
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.48</td>
210
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.26</td>
211
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.90</td>
212
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.82</td>
213
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.23</td>
214
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.22</td>
215
+ </tr><tr>
216
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">Qwen-Image-Edit-2509</td>
217
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.31</td>
218
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.34</td>
219
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.27</td>
220
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.42</td>
221
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.73</td>
222
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.36</td>
223
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.37</u></td>
224
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.91</td>
225
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.56</td>
226
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.80</td>
227
+ </tr><tr>
228
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">FLUX.2 [Dev]</td>
229
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.35</td>
230
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.50</td>
231
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.18</td>
232
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.83</td>
233
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.65</td>
234
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.65</b></td>
235
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.31</td>
236
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.88</td>
237
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.46</td>
238
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.70</td>
239
+ </tr><tr>
240
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">LongCat-Image-Edit</td>
241
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.45</td>
242
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.44</td>
243
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.53</td>
244
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.83</td>
245
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.80</b></td>
246
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.60</u></td>
247
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.33</td>
248
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.92</u></td>
249
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">3.75</td>
250
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.82</b></td>
251
+ </tr><tr>
252
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;">Qwen-Image-Edit-2511</td>
253
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.51</u></td>
254
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.54</u></td>
255
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.57</u></td>
256
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.13</u></td>
257
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.70</td>
258
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.46</td>
259
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.36</td>
260
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.89</td>
261
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.16</b></td>
262
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.81</u></td>
263
+ </tr><tr>
264
+ <td style="border:1px solid #ddd; padding:8px; text-align:left;"><b>FireRed-Image-Edit</b></td>
265
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.56</b></td>
266
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.55</b></td>
267
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.66</b></td>
268
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.34</b></td>
269
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.75</u></td>
270
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.58</td>
271
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.45</b></td>
272
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><b>4.97</b></td>
273
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;"><u>4.07</u></td>
274
+ <td style="border:1px solid #ddd; padding:8px; text-align:center;">4.71</td>
275
+ </tr></tbody>
276
+ </table>
277
+
278
+ ### Results on GEdit (official public benchmark)
279
+
280
+ <div style="overflow-x: auto; margin-bottom: 16px;">
281
+ <table style="border-collapse: collapse; width: 100%;">
282
+ <thead>
283
+ <tr>
284
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Model</th>
285
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">G_SC ↑ (EN)</th>
286
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">G_PQ ↑ (EN)</th>
287
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">G_O ↑ (EN)</th>
288
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">G_SC ↑ (CN)</th>
289
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">G_PQ ↑ (CN)</th>
290
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">G_O ↑ (CN)</th>
291
+ </tr>
292
+ </thead>
293
+ <tbody><tr>
294
+ <td colspan="7" style="padding: 8px; border: 1px solid #d0d7de; font-weight: 600; text-align: left;">🔹 Proprietary Models</td>
295
+ </tr><tr>
296
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Nano-Banana</td>
297
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.396</td>
298
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.454</strong></td>
299
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.291</td>
300
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.540</td>
301
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.424</strong></td>
302
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.399</td>
303
+ </tr><tr>
304
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Seedream4.0</td>
305
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.143</u></td>
306
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.124</td>
307
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.701</td>
308
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.159</u></td>
309
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.074</td>
310
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.692</td>
311
+ </tr><tr>
312
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Nano-Banana-Pro</td>
313
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.102</td>
314
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.344</u></td>
315
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>7.738</u></td>
316
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.135</td>
317
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.306</u></td>
318
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>7.799</u></td>
319
+ </tr><tr>
320
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Seedream4.5</td>
321
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.268</strong></td>
322
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.167</td>
323
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>7.820</strong></td>
324
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.254</strong></td>
325
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.167</td>
326
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>7.800</strong></td>
327
+ </tr><tr>
328
+ <td colspan="7" style="padding: 8px; border: 1px solid #d0d7de; font-weight: 600; text-align: left;">🔹 Open-source Models</td>
329
+ </tr><tr>
330
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">FLUX.2 [Dev]</td>
331
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.835</td>
332
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.064</td>
333
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.413</td>
334
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.697</td>
335
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.046</td>
336
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.278</td>
337
+ </tr><tr>
338
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Qwen-Image-Edit-2509</td>
339
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.974</td>
340
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.714</td>
341
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.480</td>
342
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.988</td>
343
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.679</td>
344
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.467</td>
345
+ </tr><tr>
346
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Step1X-Edit-v1.2</td>
347
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.974</td>
348
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.714</td>
349
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.480</td>
350
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.988</td>
351
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.679</td>
352
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.467</td>
353
+ </tr><tr>
354
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Longcat-Image-Edit</td>
355
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.128</td>
356
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.177</td>
357
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.748</td>
358
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.141</td>
359
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">8.117</td>
360
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">7.731</td>
361
+ </tr><tr>
362
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Qwen-Image-Edit-2511</td>
363
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.297</u></td>
364
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.202</u></td>
365
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>7.877</u></td>
366
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.252</u></td>
367
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>8.134</u></td>
368
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>7.819</u></td>
369
+ </tr><tr>
370
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;"><strong>FireRed-Image-Edit</strong></td>
371
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.363</strong></td>
372
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.245</strong></td>
373
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>7.943</strong></td>
374
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.287</strong></td>
375
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>8.227</strong></td>
376
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>7.887</strong></td>
377
+ </tr></tbody>
378
+ </table>
379
+ </div>
380
+
381
+ ### Results on REDEdit-Bench-CN (General Dimensions)
382
+
383
+ <div style="overflow-x: auto; margin-bottom: 16px;">
384
+ <table style="border-collapse: collapse; width: 100%;">
385
+ <thead>
386
+ <tr>
387
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Model</th>
388
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Overall</th>
389
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Add</th>
390
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Adjust</th>
391
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">BG</th>
392
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Beauty</th>
393
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Color</th>
394
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Compose</th>
395
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Extract</th>
396
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Portrait</th>
397
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Low-level</th>
398
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Motion</th>
399
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Remove</th>
400
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Replace</th>
401
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Stylize</th>
402
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Text</th>
403
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Viewpoint</th>
404
+ </tr>
405
+ </thead>
406
+ <tbody><tr>
407
+ <td colspan="17" style="padding: 8px; border: 1px solid #d0d7de; font-weight: 600; text-align: left;">🔹 Proprietary Models</td>
408
+ </tr><tr>
409
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Seedream4.0</td>
410
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.15</td>
411
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.55</td>
412
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.11</td>
413
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.61</u></td>
414
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.83</td>
415
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.14</u></td>
416
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.16</u></td>
417
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.48</td>
418
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.77</td>
419
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.17</u></td>
420
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.68</td>
421
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.02</td>
422
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.53</td>
423
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.94</strong></td>
424
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.94</td>
425
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.29</td>
426
+ </tr><tr>
427
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Seedream4.5</td>
428
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.18</u></td>
429
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.58</u></td>
430
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.09</td>
431
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.57</td>
432
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.97</td>
433
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.12</td>
434
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.05</td>
435
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.56</td>
436
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.80</td>
437
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.99</td>
438
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.78</u></td>
439
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.12</u></td>
440
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.53</td>
441
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.94</strong></td>
442
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.07</u></td>
443
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.53</u></td>
444
+ </tr><tr>
445
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Nano-Banana</td>
446
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.13</td>
447
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.66</strong></td>
448
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.26</u></td>
449
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.63</strong></td>
450
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.37</strong></td>
451
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.13</td>
452
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.94</td>
453
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.17</u></td>
454
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.83</u></td>
455
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.05</td>
456
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.75</td>
457
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.07</td>
458
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.74</u></td>
459
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.63</td>
460
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.69</td>
461
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.09</td>
462
+ </tr><tr>
463
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Nano-Banana-Pro</td>
464
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.48</strong></td>
465
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.66</strong></td>
466
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.41</strong></td>
467
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.58</td>
468
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.35</u></td>
469
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.58</strong></td>
470
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.36</strong></td>
471
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.42</strong></td>
472
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.86</strong></td>
473
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.46</strong></td>
474
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.91</strong></td>
475
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.54</strong></td>
476
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.79</strong></td>
477
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.85</u></td>
478
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.69</strong></td>
479
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.75</strong></td>
480
+ </tr><tr>
481
+ <td colspan="17" style="padding: 8px; border: 1px solid #d0d7de; font-weight: 600; text-align: left;">🔹 Open-source Models</td>
482
+ </tr><tr>
483
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Qwen-Image-Edit-2509</td>
484
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.00</td>
485
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.45</td>
486
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.04</td>
487
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.48</td>
488
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.36</td>
489
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.20</u></td>
490
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.92</td>
491
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.64</td>
492
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.16</td>
493
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.52</td>
494
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.66</td>
495
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.27</td>
496
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.66</td>
497
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.81</td>
498
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.53</td>
499
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.32</td>
500
+ </tr><tr>
501
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">FLUX.2 [Dev]</td>
502
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.05</td>
503
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.31</td>
504
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.88</td>
505
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.57</u></td>
506
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.80</strong></td>
507
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.91</td>
508
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.85</td>
509
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.47</td>
510
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.50</strong></td>
511
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.43</u></td>
512
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.68</strong></td>
513
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.50</td>
514
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.47</td>
515
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.95</strong></td>
516
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.53</td>
517
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.88</strong></td>
518
+ </tr><tr>
519
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Longcat-Image-Edit</td>
520
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.12</td>
521
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.34</td>
522
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.25</u></td>
523
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.54</td>
524
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.72</u></td>
525
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.12</td>
526
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.92</td>
527
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.48</td>
528
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.49</u></td>
529
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.31</td>
530
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.67</u></td>
531
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.27</td>
532
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.61</td>
533
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.94</u></td>
534
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.83</td>
535
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.30</td>
536
+ </tr><tr>
537
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Qwen-Image-Edit-2511</td>
538
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.18</u></td>
539
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.50</u></td>
540
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.23</td>
541
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.52</td>
542
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.61</td>
543
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.09</td>
544
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.00</u></td>
545
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.22</u></td>
546
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.31</td>
547
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.19</td>
548
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.66</td>
549
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.41</u></td>
550
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.68</u></td>
551
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.83</td>
552
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.08</u></td>
553
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.51</u></td>
554
+ </tr><tr>
555
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;"><strong>FireRed-Image-Edit</strong></td>
556
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.33</strong></td>
557
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.57</strong></td>
558
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.37</strong></td>
559
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.64</strong></td>
560
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.69</td>
561
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.45</strong></td>
562
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.29</strong></td>
563
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.49</strong></td>
564
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.50</strong></td>
565
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.56</strong></td>
566
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.65</td>
567
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.47</strong></td>
568
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.81</strong></td>
569
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.93</td>
570
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.49</strong></td>
571
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.14</td>
572
+ </tr></tbody>
573
+ </table>
574
+ </div>
575
+
576
+ ### Results on REDEdit-Bench-EN (General dimensions)
577
+
578
+ <div style="overflow-x: auto; margin-bottom: 16px;">
579
+ <table style="border-collapse: collapse; width: 100%;">
580
+ <thead>
581
+ <tr>
582
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Model</th>
583
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Overall</th>
584
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Add</th>
585
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Adjust</th>
586
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">BG</th>
587
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Beauty</th>
588
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Color</th>
589
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Compose</th>
590
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Extract</th>
591
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Portrait</th>
592
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Low-level</th>
593
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Motion</th>
594
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Remove</th>
595
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Replace</th>
596
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Stylize</th>
597
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Text</th>
598
+ <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa; white-space: nowrap;">Viewpoint</th>
599
+ </tr>
600
+ </thead>
601
+ <tbody><tr>
602
+ <td colspan="17" style="padding: 8px; border: 1px solid #d0d7de; font-weight: 600; text-align: left;">🔹 Proprietary Models</td>
603
+ </tr><tr>
604
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Nano-Banana</td>
605
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.15</td>
606
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.65</td>
607
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.23</u></td>
608
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.60</td>
609
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.37</strong></td>
610
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.08</td>
611
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.98</td>
612
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.39</strong></td>
613
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.72</td>
614
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.03</td>
615
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.63</td>
616
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.07</td>
617
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.68</u></td>
618
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.68</td>
619
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.87</td>
620
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.23</td>
621
+ </tr><tr>
622
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Seedream4.0</td>
623
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.18</td>
624
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.59</td>
625
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.12</td>
626
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.63</u></td>
627
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.89</td>
628
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.10</u></td>
629
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.14</u></td>
630
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.28</td>
631
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.77</u></td>
632
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.12</td>
633
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.73</td>
634
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.23</td>
635
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.56</td>
636
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.98</strong></td>
637
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.21</u></td>
638
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.42</td>
639
+ </tr><tr>
640
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Seedream4.5</td>
641
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.20</u></td>
642
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.66</u></td>
643
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.08</td>
644
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.64</strong></td>
645
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.12</u></td>
646
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.07</td>
647
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.10</td>
648
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.23</td>
649
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.74</td>
650
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.28</u></td>
651
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.75</u></td>
652
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.24</u></td>
653
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.58</td>
654
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.97</u></td>
655
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.20</td>
656
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.44</u></td>
657
+ </tr><tr>
658
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Nano-Banana-Pro</td>
659
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.42</strong></td>
660
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.72</strong></td>
661
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.40</strong></td>
662
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.64</strong></td>
663
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.37</strong></td>
664
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.43</strong></td>
665
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.32</strong></td>
666
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.25</u></td>
667
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.82</strong></td>
668
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.36</strong></td>
669
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.85</strong></td>
670
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.52</strong></td>
671
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.75</strong></td>
672
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.90</td>
673
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.54</strong></td>
674
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.51</strong></td>
675
+ </tr><tr>
676
+ <td colspan="17" style="padding: 8px; border: 1px solid #d0d7de; font-weight: 600; text-align: left;">🔹 Open-source Models</td>
677
+ </tr><tr>
678
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Qwen-Image-Edit-2509</td>
679
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.99</td>
680
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.47</u></td>
681
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.06</td>
682
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.49</td>
683
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.13</td>
684
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.98</td>
685
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.85</td>
686
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.91</td>
687
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.30</td>
688
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.71</td>
689
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.58</td>
690
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.40</td>
691
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.67</u></td>
692
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.77</td>
693
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.77</td>
694
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.85</td>
695
+ </tr><tr>
696
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">FLUX.2 [Dev]</td>
697
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.07</td>
698
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.37</td>
699
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.96</td>
700
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.47</td>
701
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.72</u></td>
702
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.86</td>
703
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.87</td>
704
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.36</td>
705
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.44</td>
706
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.45</u></td>
707
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.67</td>
708
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.02</td>
709
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.48</td>
710
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.87</u></td>
711
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.80</td>
712
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.84</strong></td>
713
+ </tr><tr>
714
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">LongCat-Image-Edit</td>
715
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.12</td>
716
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.38</td>
717
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.04</td>
718
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.49</td>
719
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.89</strong></td>
720
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.10</u></td>
721
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.93</td>
722
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.98</td>
723
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.47</u></td>
724
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.27</td>
725
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.69</u></td>
726
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.24</td>
727
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.51</td>
728
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.86</td>
729
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.83</td>
730
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.25</td>
731
+ </tr><tr>
732
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;">Qwen-Image-Edit-2511</td>
733
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.23</u></td>
734
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.55</strong></td>
735
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.17</u></td>
736
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.56</u></td>
737
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.49</td>
738
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.07</td>
739
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.07</u></td>
740
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>3.54</strong></td>
741
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.42</td>
742
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.52</strong></td>
743
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.72</strong></td>
744
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.42</u></td>
745
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.65</td>
746
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.85</td>
747
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>4.06</u></td>
748
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.38</u></td>
749
+ </tr><tr>
750
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: left; white-space: nowrap;"><strong>FireRed-Image-Edit</strong></td>
751
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.26</strong></td>
752
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.41</td>
753
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.33</strong></td>
754
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.60</strong></td>
755
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">3.55</td>
756
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.47</strong></td>
757
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.25</strong></td>
758
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><u>3.49</u></td>
759
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.50</strong></td>
760
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.44</td>
761
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">4.65</td>
762
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.46</strong></td>
763
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.70</strong></td>
764
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.94</strong></td>
765
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;"><strong>4.44</strong></td>
766
+ <td style="padding: 8px; border: 1px solid #d0d7de; text-align: center; white-space: nowrap;">2.78</td>
767
+ </tr></tbody>
768
+ </table>
769
+ </div>
770
+
771
+ ## 📜 License Agreement
772
+
773
+ The code and the weights of FireRed-Image-Edit are licensed under Apache 2.0.
774
+
775
+
776
+ ## 📝 TODO:
777
+ - [x] Release FireRed-Image-Edit-1.0 model.
778
+ - [ ] Release REDEdit-Bench, a comprehensive benchmark for image editing evaluation.
779
+ - [ ] Release FireRed-Image-Edit-1.0-Distilled model, a distilled version of FireRed-Image-Edit-1.0 for few-step generation.
780
+ - [ ] Release FireRed-Image model, a text-to-image generative model.
781
+
782
+
783
+ ## 🖊️ Citation
784
+
785
+ We kindly encourage citation of our work if you find it useful.
786
+
787
+ ```bibtex
788
+ @article{firered2026rededit,
789
+ title={FireRed-Image-Edit: A General-Purpose Image Editing Model},
790
+ author={Super Intelligence Team},
791
+ year={2026},
792
+ archivePrefix={arXiv},
793
+ primaryClass={cs.CV},
794
+ url={https://arxiv.org/abs/xxxx.xxxxx},
795
+ }
796
+ ```
797
+
798
+ ## ⚠️ Ethics Statement
799
+ FireRed-Image-Edit has not been specifically designed or comprehensively evaluated for every possible downstream application. Users should be aware of the potential risks and ethical considerations when using this project, and should use it responsibly and in compliance with all applicable laws and regulations.
800
+
801
+ - **Prohibited Use**: This project must not be used to generate content that is illegal, defamatory, pornographic, harmful, or that violates the privacy, rights, or interests of individuals or organizations.
802
+ - **User Responsibility**: Users are solely responsible for any content generated using this project. The authors and contributors assume no responsibility or liability for any misuse of the codebase or for any consequences resulting from its use.
803
+
804
+
805
+
806
+ ## 🤝 Acknowledgements
807
+
808
+ We would like to thank the developers of the amazing open-source projects, including [Qwen-Image](https://github.com/QwenLM/Qwen-Image), [Diffusers](https://github.com/huggingface/diffusers) and [HuggingFace](https://huggingface.co)
809
+
810
+ ## ⭐ Star History
811
+
812
+ [![Star History Chart](https://api.star-history.com/svg?repos=FireRedTeam/FireRed-Image-Edit&type=date&legend=top-left)](https://www.star-history.com/#FireRedTeam/FireRed-Image-Edit&type=date&legend=top-left)
assets/architecture.png ADDED

Git LFS Details

  • SHA256: deec5bf77065272ddfc4dd81a0b012526032c0e67a92f9bbd7356da77aea7f3a
  • Pointer size: 132 Bytes
  • Size of remote file: 1.02 MB
assets/logo.png ADDED

Git LFS Details

  • SHA256: f62889edf930245dbc59c8b1deed104b694e6cabaeb085c5ec628774c33b7495
  • Pointer size: 131 Bytes
  • Size of remote file: 224 kB
assets/showcase.png ADDED

Git LFS Details

  • SHA256: be26bc858c82e5f9c5d9a9d763db3f51ec27729de50e4929b0d0669b9225360a
  • Pointer size: 132 Bytes
  • Size of remote file: 3.42 MB
assets/teaser.png ADDED

Git LFS Details

  • SHA256: 46d32dfa5de1f8596e0137693aca72daa0771727677b51dddefea0bc1cf67048
  • Pointer size: 132 Bytes
  • Size of remote file: 5.57 MB
model_index.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImageEditPlusPipeline",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "processor": [
5
+ "transformers",
6
+ "Qwen2VLProcessor"
7
+ ],
8
+ "scheduler": [
9
+ "diffusers",
10
+ "FlowMatchEulerDiscreteScheduler"
11
+ ],
12
+ "text_encoder": [
13
+ "transformers",
14
+ "Qwen2_5_VLForConditionalGeneration"
15
+ ],
16
+ "tokenizer": [
17
+ "transformers",
18
+ "Qwen2Tokenizer"
19
+ ],
20
+ "transformer": [
21
+ "diffusers",
22
+ "QwenImageTransformer2DModel"
23
+ ],
24
+ "vae": [
25
+ "diffusers",
26
+ "AutoencoderKLQwenImage"
27
+ ]
28
+ }
processor/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
processor/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% 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
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% 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|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
processor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
processor/preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_pixels": 3136,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 12845056,
36
+ "shortest_edge": 3136
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
processor/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
processor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
processor/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
processor/video_preprocessor_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "pad_size": null,
32
+ "patch_size": 14,
33
+ "processor_class": "Qwen2VLProcessor",
34
+ "resample": 3,
35
+ "rescale_factor": 0.00392156862745098,
36
+ "return_metadata": false,
37
+ "size": {
38
+ "longest_edge": 12845056,
39
+ "shortest_edge": 3136
40
+ },
41
+ "size_divisor": null,
42
+ "temporal_patch_size": 2,
43
+ "video_metadata": null,
44
+ "video_processor_type": "Qwen2VLVideoProcessor"
45
+ }
processor/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 8192,
8
+ "max_shift": 0.9,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": 0.02,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "text_config": {
32
+ "architectures": [
33
+ "Qwen2_5_VLForConditionalGeneration"
34
+ ],
35
+ "attention_dropout": 0.0,
36
+ "bos_token_id": 151643,
37
+ "dtype": "bfloat16",
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 3584,
41
+ "image_token_id": 151655,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 18944,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention"
73
+ ],
74
+ "max_position_embeddings": 128000,
75
+ "max_window_layers": 28,
76
+ "model_type": "qwen2_5_vl_text",
77
+ "num_attention_heads": 28,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 4,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_scaling": {
82
+ "mrope_section": [
83
+ 16,
84
+ 24,
85
+ 24
86
+ ],
87
+ "rope_type": "default",
88
+ "type": "default"
89
+ },
90
+ "rope_theta": 1000000.0,
91
+ "sliding_window": null,
92
+ "use_cache": true,
93
+ "use_sliding_window": false,
94
+ "video_token_id": 151656,
95
+ "vision_end_token_id": 151653,
96
+ "vision_start_token_id": 151652,
97
+ "vision_token_id": 151654,
98
+ "vocab_size": 152064
99
+ },
100
+ "tie_word_embeddings": false,
101
+ "transformers_version": "4.57.1",
102
+ "use_cache": true,
103
+ "use_sliding_window": false,
104
+ "vision_config": {
105
+ "depth": 32,
106
+ "dtype": "bfloat16",
107
+ "fullatt_block_indexes": [
108
+ 7,
109
+ 15,
110
+ 23,
111
+ 31
112
+ ],
113
+ "hidden_act": "silu",
114
+ "hidden_size": 1280,
115
+ "in_channels": 3,
116
+ "in_chans": 3,
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3420,
119
+ "model_type": "qwen2_5_vl",
120
+ "num_heads": 16,
121
+ "out_hidden_size": 3584,
122
+ "patch_size": 14,
123
+ "spatial_merge_size": 2,
124
+ "spatial_patch_size": 14,
125
+ "temporal_patch_size": 2,
126
+ "tokens_per_second": 2,
127
+ "window_size": 112
128
+ },
129
+ "vision_token_id": 151654,
130
+ "vocab_size": 152064
131
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.1,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.57.1"
14
+ }
text_encoder/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4
3
+ size 4968243304
text_encoder/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1830db6908dcc76df3a71492acbcf2b8cac130114cf1f3c2d9edae8de8c6de3
3
+ size 4991495816
text_encoder/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c1807c6d00d7cab94f7db39d4c02ebb8537225ccde383861ac48db97945aa6
3
+ size 4932751040
text_encoder/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd068336d14d45ffb43cef374d286cc6ba9d8741b028f90a7d040d847961f4a
3
+ size 1691924384
text_encoder/model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8292166656,
4
+ "total_size": 16584333312
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImageTransformer2DModel",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "attention_head_dim": 128,
5
+ "axes_dims_rope": [
6
+ 16,
7
+ 56,
8
+ 56
9
+ ],
10
+ "guidance_embeds": false,
11
+ "in_channels": 64,
12
+ "joint_attention_dim": 3584,
13
+ "num_attention_heads": 24,
14
+ "num_layers": 60,
15
+ "out_channels": 16,
16
+ "patch_size": 2
17
+ }
transformer/diffusion_pytorch_model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04e3ec3cb1123b7f4bd4363a861ec1416e91b22eac7742f3227e724ecae41ea
3
+ size 9973578592
transformer/diffusion_pytorch_model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56ef87d97f4ea50135074079066a0dc67ca257b5a8a8b273ecff629fd9a6b879
3
+ size 9987326072
transformer/diffusion_pytorch_model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1426c424894f36dec1829e79591a241ae029df2ef3b0ecfe76b205249dc12c95
3
+ size 9987307440
transformer/diffusion_pytorch_model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f770a8769373ac4cff82303ef5de032a9337473a797df2e4d49851375a575880
3
+ size 9930685712
transformer/diffusion_pytorch_model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50388f3b1e7881cadf901db4e3f04db8d3408bd19b88e76c52e20d5e38679d57
3
+ size 982130472
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLQwenImage",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "attn_scales": [],
5
+ "base_dim": 96,
6
+ "dim_mult": [
7
+ 1,
8
+ 2,
9
+ 4,
10
+ 4
11
+ ],
12
+ "dropout": 0.0,
13
+ "latents_mean": [
14
+ -0.7571,
15
+ -0.7089,
16
+ -0.9113,
17
+ 0.1075,
18
+ -0.1745,
19
+ 0.9653,
20
+ -0.1517,
21
+ 1.5508,
22
+ 0.4134,
23
+ -0.0715,
24
+ 0.5517,
25
+ -0.3632,
26
+ -0.1922,
27
+ -0.9497,
28
+ 0.2503,
29
+ -0.2921
30
+ ],
31
+ "latents_std": [
32
+ 2.8184,
33
+ 1.4541,
34
+ 2.3275,
35
+ 2.6558,
36
+ 1.2196,
37
+ 1.7708,
38
+ 2.6052,
39
+ 2.0743,
40
+ 3.2687,
41
+ 2.1526,
42
+ 2.8652,
43
+ 1.5579,
44
+ 1.6382,
45
+ 1.1253,
46
+ 2.8251,
47
+ 1.916
48
+ ],
49
+ "num_res_blocks": 2,
50
+ "temperal_downsample": [
51
+ false,
52
+ true,
53
+ true
54
+ ],
55
+ "z_dim": 16
56
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344
3
+ size 253806966