Hugging Face's logo

jsoncx
/
HiDream-O1-Image-Dev

Image-Text-to-Image
Transformers
Safetensors
qwen3_vl
image-text-to-text
Model card Files
xet
 Community
jsoncx commited on
Commit
2d461e9
·
verified ·
1 Parent(s): fc8f64e

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +5 -0
  2. .mdl +0 -0
  3. .msc +0 -0
  4. .mv +1 -0
  5. README.md +379 -0
  6. assets/IP.webp +3 -0
  7. assets/IP_2.jpg +3 -0
  8. assets/general.webp +3 -0
  9. assets/leaderboard.png +3 -0
  10. assets/text-layout.webp +3 -0
  11. chat_template.json +3 -0
  12. config.json +62 -0
  13. configuration.json +1 -0
  14. generation_config.json +14 -0
  15. merges.txt +0 -0
  16. model-00001-of-00008.safetensors +3 -0
  17. model-00002-of-00008.safetensors +3 -0
  18. model-00003-of-00008.safetensors +3 -0
  19. model-00004-of-00008.safetensors +3 -0
  20. model-00005-of-00008.safetensors +3 -0
  21. model-00006-of-00008.safetensors +3 -0
  22. model-00007-of-00008.safetensors +3 -0
  23. model-00008-of-00008.safetensors +3 -0
  24. model.safetensors.index.json +767 -0
  25. preprocessor_config.json +21 -0
  26. tokenizer.json +0 -0
  27. tokenizer_config.json +244 -0
  28. video_preprocessor_config.json +21 -0
  29. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ assets/general.webp filter=lfs diff=lfs merge=lfs -text
37
+ assets/IP.webp filter=lfs diff=lfs merge=lfs -text
38
+ assets/text-layout.webp filter=lfs diff=lfs merge=lfs -text
39
+ assets/leaderboard.png filter=lfs diff=lfs merge=lfs -text
40
+ assets/IP_2.jpg filter=lfs diff=lfs merge=lfs -text
.mdl ADDED
Binary file (48 Bytes). View file
 
.msc ADDED
Binary file (1.24 kB). View file
 
.mv ADDED
@@ -0,0 +1 @@
 
 
1
+ Revision:master,CreatedAt:1760445354
README.md ADDED
@@ -0,0 +1,379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ pipeline_tag: image-text-to-image
4
+ library_name: transformers
5
+ ---
6
+ # HiDream-O1-Image
7
+
8
+ HiDream-O1-Image is a natively unified image generative foundation model built on a Pixel-level Unified Transformer (UiT) without external VAEs or disjoint text encoders, which natively encodes raw pixels, text, and task-specific conditions in a single shared token space — supporting text-to-image, image editing, and subject-driven personalization at up to 2,048 × 2,048.
9
+
10
+ ## Project Updates
11
+ - 💬 **June 22, 2026:** Join our Discord community for questions, support, and discussions. <a href="https://discord.gg/7ZEnPxdTQ"><img src="https://img.shields.io/badge/Discord-Join%20Community-5865F2.svg?style=flat&amp;logo=discord&amp;logoColor=white" alt="Discord" /></a>
12
+ - 🚀 **May 14, 2026:** We open-sourced [**HiDream-O1-Image-Dev-2604**](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev-2604) with its [prompt refiner](https://huggingface.co/HiDream-ai/Prompt-Refine), tailored for text-to-image generation task.
13
+ - 🛠️ **May 13, 2026:** Inference & pipeline updates — accelerated IP inference; the IP pipeline now supports **layout** and **skeleton** conditioning; updated the Dev editing scheduler. For editing tasks we recommend using the **full** model. PyTorch 2.9.x is not recommended due to the [issue](https://github.com/QwenLM/Qwen3-VL/issues/1811).
14
+ - 🤗 **May 10, 2026:** Try **HiDream-O1-Image** online on Hugging Face Spaces — [🤗 HiDream-O1-Image](https://huggingface.co/spaces/HiDream-ai/HiDream-O1-Image) and [🤗 HiDream-O1-Image-Dev](https://huggingface.co/spaces/HiDream-ai/HiDream-O1-Image-Dev).
15
+ - 📕 **May 10, 2026:** Our **technical report** is now available — [📑 HiDream-O1-Image.pdf](https://arxiv.org/pdf/2605.11061v1).
16
+ - 🚀 **May 8, 2026:** We've open-sourced **HiDream-O1-Image (8B)**, including both the undistilled and distilled Dev variants, together with the Reasoning-Driven Prompt Agent.
17
+
18
+ > **HiDream-O1-Image-Dev-2604 debuts at #8 in the Artificial Analysis Text to Image Arena, which is positioned to be the new leading open weights Text to Image model.**
19
+ <p align="center">
20
+ <img src="assets/leaderboard.png" alt="Artificial Analysis Text to Image Arena" width="100%"/>
21
+ <br><sub><b>Artificial Analysis Text to Image Arena</b> at up to 2,048 × 2,048.</sub>
22
+ </p>
23
+
24
+ <p align="center">
25
+ <img src="assets/general.webp" alt="General text-to-image generation" width="100%"/>
26
+ <br><sub><b>General text-to-image generation</b> at up to 2,048 × 2,048.</sub>
27
+ </p>
28
+
29
+ <p align="center">
30
+ <img src="assets/text-layout.webp" alt="Long-text rendering and layout" width="100%"/>
31
+ <br><sub><b>Long-text rendering & layout control</b> — accurate, multi-region, multilingual text.</sub>
32
+ </p>
33
+
34
+ <p align="center">
35
+ <img src="assets/IP_2.jpg" alt="Subject-driven personalization" width="100%"/>
36
+ <br><sub><b>Subject-driven personalization</b> — preserve identity / IP across new scenes.</sub>
37
+ </p>
38
+
39
+ ## Key Features
40
+
41
+ - 🧬 **Pixel-Level Unified Transformer** — One end-to-end model on raw pixels, no VAE, no disjoint text encoder.
42
+ - 🎨 **One Model, Many Tasks** — Text-to-image, long-text rendering, instruction editing, subject-driven personalization, and storyboard generation in a single architecture.
43
+ - 🧠 **Reasoning-Driven Prompt Agent** — Built-in "thinking" agent that resolves implicit knowledge, layout, and text rendering before generation.
44
+ - 🖼️ **Native High Resolution** — Direct synthesis up to 2,048 × 2,048 with sharp fine-grained detail.
45
+ - ⚡ **Exceptional Efficiency and Versatility at 8B Scale** — With only 8B parameters, achieves performance parity with or even surpasses larger open-source DiTs and leading closed-source models.
46
+
47
+
48
+
49
+ ## Models
50
+
51
+ | Name | Script | Inference Steps | HuggingFace Repo |
52
+ | :--- | :--- | :---: | :--- |
53
+ | HiDream-O1-Image | [`inference.py`](https://github.com/HiDream-ai/HiDream-O1-Image/blob/main/inference.py) | 50 | [🤗 HiDream-O1-Image](https://huggingface.co/HiDream-ai/HiDream-O1-Image) |
54
+ | HiDream-O1-Image-Dev | [`inference.py`](https://github.com/HiDream-ai/HiDream-O1-Image/blob/main/inference.py) | 28 | [🤗 HiDream-O1-Image-Dev](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev) |
55
+ | Prompt Agent | [`prompt_agent.py`](https://github.com/HiDream-ai/HiDream-O1-Image/blob/main/prompt_agent.py) | — | [🤗 google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it) |
56
+ | Web Demo | [`app.py`](https://github.com/HiDream-ai/HiDream-O1-Image/blob/main/app.py) | — | — |
57
+ | HiDream-O1-Image-Dev-2604 | [`inference.py` (dev branch)](https://github.com/HiDream-ai/HiDream-O1-Image/blob/dev/inference.py) | 28 | [🤗 HiDream-O1-Image-Dev-2604](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev-2604) |
58
+ | Prompt Agent 2604 | [`prompt_agent_v2.py` (dev branch)](https://github.com/HiDream-ai/HiDream-O1-Image/blob/dev/prompt_agent_v2.py) | — | [🤗 HiDream-ai/Prompt-Refine](https://huggingface.co/HiDream-ai/Prompt-Refine) |
59
+
60
+ ## Evaluation
61
+
62
+ We benchmark HiDream-O1-Image against state-of-the-art open-source and proprietary models on five widely-used evaluation suites covering compositional generation, dense prompt alignment, human preference, complex visual text generation, and long-text rendering. In each table, the **best** result is highlighted in bold and the <u>second-best</u> is underlined. Click any benchmark below to expand or collapse.
63
+
64
+ <details open>
65
+ <summary><b>GenEval</b> — compositional generation</summary>
66
+
67
+ | Model | #Params | Single-Obj | Two-Obj | Count | Color | Position | Attr | Overall |
68
+ | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
69
+ | Nano Banana 2.0 | – | 1.00 | 0.96 | 0.71 | 0.84 | 0.86 | 0.65 | 0.83 |
70
+ | Seedream-4.0 | – | 1.00 | 0.92 | 0.71 | 0.93 | 0.78 | 0.68 | 0.84 |
71
+ | GPT Image 1 [High] | – | 0.99 | 0.92 | 0.85 | 0.92 | 0.75 | 0.61 | 0.84 |
72
+ | GPT Image 2 | – | 0.99 | 0.98 | 0.85 | 0.93 | 0.85 | 0.77 | 0.89 |
73
+ | PixArt | 4.3B + 0.6B | 0.98 | 0.50 | 0.44 | 0.80 | 0.08 | 0.07 | 0.48 |
74
+ | Show-o | 1.3B | 0.95 | 0.52 | 0.49 | 0.82 | 0.11 | 0.28 | 0.53 |
75
+ | Emu3-Gen | 8B | 0.98 | 0.71 | 0.34 | 0.81 | 0.17 | 0.21 | 0.54 |
76
+ | SD3-Medium | 5.5B + 2B | 0.98 | 0.74 | 0.63 | 0.67 | 0.34 | 0.36 | 0.62 |
77
+ | JanusFlow | 1.3B | 0.97 | 0.59 | 0.45 | 0.83 | 0.53 | 0.42 | 0.63 |
78
+ | FLUX.1 [Dev] | 4.8B + 12B | 0.98 | 0.81 | 0.74 | 0.79 | 0.22 | 0.45 | 0.66 |
79
+ | SD3.5 Large | 5.5B + 8.1B | 0.98 | 0.89 | 0.73 | 0.83 | 0.34 | 0.47 | 0.71 |
80
+ | Janus-Pro-7B | 7B | 0.99 | 0.89 | 0.59 | 0.90 | 0.79 | 0.66 | 0.80 |
81
+ | Z-Image-Turbo | 4B + 6B | 1.00 | 0.95 | 0.77 | 0.89 | 0.65 | 0.68 | 0.82 |
82
+ | FLUX.2 [Dev] | 24B + 32B | 1.00 | 0.99 | 0.79 | 0.93 | 0.73 | 0.78 | 0.87 |
83
+ | Qwen-Image | 7B + 20B | 0.99 | 0.92 | 0.89 | 0.88 | 0.76 | 0.77 | 0.87 |
84
+ | **HiDream-O1-Image** | 8B | 1.00 | 0.99 | 0.79 | 0.89 | 0.93 | 0.78 | <u>0.90</u> |
85
+ | **HiDream-O1-Image-Pro** | 200B+ | 1.00 | 0.99 | 0.85 | 0.94 | 0.94 | 0.79 | **0.92** |
86
+
87
+ </details>
88
+
89
+ <details open>
90
+ <summary><b>DPG-Bench</b> — dense prompt alignment</summary>
91
+
92
+ | Model | #Params | Global | Entity | Attribute | Relation | Other | Overall |
93
+ | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
94
+ | GPT Image 1 [High] | – | 88.89 | 88.94 | 89.84 | 92.63 | 90.96 | 85.15 |
95
+ | GPT Image 2 | – | 87.27 | 91.91 | 90.85 | 91.59 | 91.58 | 85.98 |
96
+ | Nano Banana 2.0 | – | 85.17 | 92.55 | 91.16 | 90.45 | 91.08 | 86.90 |
97
+ | Seedream-4.0 | – | 87.17 | 92.41 | 92.29 | 93.33 | 95.48 | 88.63 |
98
+ | SD v1.5 | 0.12B + 0.86B | 74.63 | 74.23 | 75.39 | 73.49 | 67.81 | 63.18 |
99
+ | PixArt | 4.3B + 0.6B | 74.97 | 79.32 | 78.60 | 82.57 | 76.96 | 71.11 |
100
+ | Lumina-Next | 2B + 2B | 82.82 | 88.65 | 86.44 | 80.53 | 81.82 | 74.63 |
101
+ | SDXL | 0.81B + 2.6B | 83.27 | 82.43 | 80.91 | 86.76 | 80.41 | 74.65 |
102
+ | Hunyuan-DiT | 4.8B + 1.5B | 84.59 | 80.59 | 88.01 | 74.36 | 86.41 | 78.87 |
103
+ | Emu3-Gen | 8B | 85.21 | 86.68 | 86.84 | 90.22 | 83.15 | 80.60 |
104
+ | DALL-E 3 | – | 90.97 | 89.61 | 88.39 | 90.58 | 89.83 | 83.50 |
105
+ | FLUX.1 [Dev] | 4.8B + 12B | 74.35 | 90.00 | 88.96 | 90.87 | 88.33 | 83.84 |
106
+ | SD3 Medium | 5.5B + 2B | 87.90 | 91.01 | 88.83 | 80.70 | 88.68 | 84.08 |
107
+ | Janus-Pro-7B | 7B | 86.90 | 88.90 | 89.40 | 89.32 | 89.48 | 84.19 |
108
+ | Z-Image-Turbo | 4B + 6B | 91.29 | 89.59 | 90.14 | 92.16 | 88.68 | 84.86 |
109
+ | HiDream-I1-Full | 13.5B + 17B | 76.44 | 90.22 | 89.48 | 93.74 | 91.83 | 85.89 |
110
+ | FLUX.2 [Dev] | 24B + 32B | 92.20 | 91.36 | 93.28 | 93.52 | 89.72 | 87.57 |
111
+ | Qwen-Image | 7B + 20B | 91.32 | 91.56 | 92.02 | 94.31 | 92.73 | 88.32 |
112
+ | **HiDream-O1-Image** | 8B | 95.15 | 92.32 | 93.74 | 92.88 | 90.25 | <u>89.83</u> |
113
+ | **HiDream-O1-Image-Pro** | 200B+ | 94.97 | 95.42 | 92.59 | 90.82 | 89.50 | **90.30** |
114
+
115
+ </details>
116
+
117
+ <details open>
118
+ <summary><b>HPSv3</b> — human preference across 12 categories</summary>
119
+
120
+ | Model | #Params | All | Characters | Arts | Design | Architecture | Animals | Natural Scenery | Transportation | Products | Plants | Food | Science | Others |
121
+ | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
122
+ | Seedream-4.0 | – | 9.32 | 9.83 | 9.20 | 8.83 | 9.95 | 8.99 | 9.40 | 9.58 | 9.12 | 9.26 | 9.75 | 9.11 | 9.51 |
123
+ | Nano Banana 2.0 | – | 10.01 | 10.18 | 9.18 | 9.58 | 10.96 | 9.71 | 10.04 | 10.38 | 10.36 | 10.14 | 10.61 | 9.14 | 9.89 |
124
+ | GPT Image 2 | – | 10.21 | 10.75 | 9.91 | 10.15 | 10.59 | 10.05 | 10.29 | 10.17 | 10.26 | 10.07 | 10.75 | 10.05 | 10.00 |
125
+ | Z-Image-Turbo | 4B + 6B | 8.35 | 8.98 | 8.29 | 7.65 | 9.26 | 8.51 | 8.33 | 8.81 | 7.83 | 8.46 | 8.64 | 7.93 | 8.57 |
126
+ | FLUX.2 [Dev] | 24B + 32B | 9.28 | 10.23 | 9.56 | 8.80 | 9.73 | 9.43 | 9.21 | 9.44 | 8.93 | 9.23 | 9.82 | 8.67 | 9.11 |
127
+ | Qwen-Image | 7B + 20B | 9.94 | 10.91 | 10.47 | 9.56 | 10.22 | 10.61 | 9.87 | 10.10 | 9.15 | 9.99 | 10.08 | 9.19 | 9.83 |
128
+ | **HiDream-O1-Image** | 8B | <u>10.37</u> | 10.59 | 10.44 | 10.29 | 11.02 | 10.34 | 10.37 | 10.54 | 10.50 | 10.38 | 10.85 | 9.68 | 10.09 |
129
+ | **HiDream-O1-Image-Pro** | 200B+ | **10.47** | 10.63 | 10.51 | 10.33 | 11.11 | 10.08 | 10.45 | 10.37 | 10.75 | 10.29 | 11.13 | 10.09 | 10.39 |
130
+
131
+ </details>
132
+
133
+ <details>
134
+ <summary><b>CVTG-2K</b> — complex visual text generation (click to expand)</summary>
135
+
136
+ | Model | #Params | 2 regions | 3 regions | 4 regions | 5 regions | Average | NED | CLIP Score |
137
+ | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
138
+ | Nano Banana 2.0 | – | 0.7465 | 0.7720 | 0.8067 | 0.7980 | 0.7875 | 0.8945 | 0.7212 |
139
+ | GPT Image 1 [High] | – | 0.8779 | 0.8659 | 0.8731 | 0.8218 | 0.8569 | 0.9478 | 0.7982 |
140
+ | Seedream-4.0 | – | 0.8980 | 0.8949 | 0.9044 | 0.9015 | 0.9003 | 0.9511 | 0.8033 |
141
+ | GPT Image 2 | – | 0.8904 | 0.8887 | 0.9101 | 0.9044 | 0.9003 | 0.9515 | 0.7798 |
142
+ | TextDiffuser-2 | 0.12B + 0.9B | 0.5322 | 0.3255 | 0.1787 | 0.0809 | 0.2326 | 0.4353 | 0.6765 |
143
+ | RAG-Diffusion | 4.8B + 12B | 0.4388 | 0.3316 | 0.2116 | 0.1910 | 0.2648 | 0.4498 | 0.7797 |
144
+ | AnyText | 0.123B + 1.2B | 0.0513 | 0.1739 | 0.1948 | 0.2249 | 0.1804 | 0.4675 | 0.7432 |
145
+ | 3DIS | 0.81B + 2.6B | 0.4495 | 0.3959 | 0.3880 | 0.3303 | 0.3813 | 0.6505 | 0.7767 |
146
+ | FLUX.1 [Dev] | 4.8B + 12B | 0.6089 | 0.5531 | 0.4661 | 0.4316 | 0.4965 | 0.6879 | 0.7401 |
147
+ | SD3.5 Large | 5.5B + 8.1B | 0.7293 | 0.6825 | 0.6574 | 0.5940 | 0.6548 | 0.8470 | 0.7797 |
148
+ | TextCrafter | 7B + 20B | 0.7628 | 0.7628 | 0.7406 | 0.6977 | 0.7370 | 0.8679 | 0.7868 |
149
+ | Qwen-Image | 7B + 20B | 0.8370 | 0.8364 | 0.8313 | 0.8158 | 0.8288 | 0.9116 | 0.8017 |
150
+ | Z-Image-Turbo | 4B + 6B | 0.8872 | 0.8662 | 0.8628 | 0.8347 | 0.8585 | 0.9281 | 0.8048 |
151
+ | FLUX.2 [Dev] | 24B + 32B | 0.9261 | 0.8897 | 0.8995 | 0.8732 | 0.8926 | 0.9475 | <u>0.8104</u> |
152
+ | **HiDream-O1-Image** | 8B | 0.9085 | 0.9159 | 0.9216 | 0.9015 | <u>0.9128</u> | <u>0.9561</u> | 0.8076 |
153
+ | **HiDream-O1-Image-Pro** | 200B+ | 0.9133 | 0.9221 | 0.9365 | 0.9175 | **0.9222** | **0.9628** | **0.8349** |
154
+
155
+ </details>
156
+
157
+ <details>
158
+ <summary><b>LongText-Bench</b> — long-text rendering, EN & ZH (click to expand)</summary>
159
+
160
+ | Model | #Params | LongText-Bench-EN | LongText-Bench-ZH |
161
+ | :--- | :---: | :---: | :---: |
162
+ | Seedream-4.0 | – | 0.936 | 0.946 |
163
+ | GPT Image 1 [High] | – | 0.956 | 0.619 |
164
+ | GPT Image 2 | – | 0.960 | 0.961 |
165
+ | Nano Banana 2.0 | – | <u>0.980</u> | 0.965 |
166
+ | Janus-Pro-7B | 7B | 0.019 | 0.006 |
167
+ | BLIP3-o | 7B + 1.4B | 0.021 | 0.018 |
168
+ | Kolors 2.0 | – | 0.258 | 0.329 |
169
+ | BAGEL | 7B + 7B | 0.373 | 0.310 |
170
+ | OmniGen2 | 3B + 4B | 0.561 | 0.059 |
171
+ | X-Omni | 7B | 0.900 | 0.814 |
172
+ | HiDream-I1-Full | 13.5B + 17B | 0.543 | 0.024 |
173
+ | FLUX.1 [Dev] | 4.8B + 12B | 0.607 | 0.005 |
174
+ | Z-Image-Turbo | 4B + 6B | 0.917 | 0.926 |
175
+ | FLUX.2 [Dev] | 24B + 32B | 0.963 | 0.757 |
176
+ | Qwen-Image | 7B + 20B | 0.943 | 0.946 |
177
+ | **HiDream-O1-Image** | 8B | 0.979 | <u>0.978</u> |
178
+ | **HiDream-O1-Image-Pro** | 200B+ | **0.982** | **0.980** |
179
+
180
+ </details>
181
+
182
+ ## Installation
183
+
184
+ 1. Clone this repository:
185
+ ```bash
186
+ git clone https://github.com/HiDream-ai/HiDream-O1-Image.git
187
+ cd HiDream-O1-Image
188
+ ```
189
+
190
+ 2. Install the required dependencies:
191
+ ```bash
192
+ pip install -r requirements.txt
193
+ ```
194
+
195
+ > **Note on `flash-attn`.** We highly recommend installing [`flash-attn`](https://github.com/Dao-AILab/flash-attention) for optimized attention computation. **If you do not (or cannot) install `flash-attn`, you must edit `models/pipeline.py` line 341 and change `"use_flash_attn": True` to `"use_flash_attn": False`** — otherwise inference will fail to import the kernel.
196
+
197
+ ## Reasoning-Driven Prompt Agent
198
+
199
+ HiDream-O1-Image ships with a Reasoning-Driven Prompt Agent (`prompt_agent.py`) that explicitly reasons through layout, subject attributes, physical logic, and text-rendering details, then rewrites a raw user instruction into a self-contained English prompt. It supports two backends — pick one with `--backend`.
200
+
201
+ The agent prints a JSON object with three fields: `prompt` (rewritten English prompt), `reasoning`, and `resolved_knowledge`. Feed the `prompt` field into `inference.py` for best results on intricate, reasoning-heavy requests.
202
+
203
+ ### Option A — Local Backend (Gemma-4-31B-it)
204
+
205
+ 1. Download the Gemma weights (requires accepting the Gemma license on HuggingFace):
206
+ ```bash
207
+ huggingface-cli download google/gemma-4-31B-it --local-dir /path/to/gemma-4-31B-it
208
+ ```
209
+
210
+ 2. Run the refiner locally:
211
+ ```bash
212
+ python prompt_agent.py \
213
+ --backend local \
214
+ --model_id /path/to/gemma-4-31B-it \
215
+ --prompt "李白的静夜思写在古墙上"
216
+ ```
217
+
218
+ ### Option B — External OpenAI-Compatible API
219
+
220
+ Use any OpenAI-compatible endpoint (OpenAI, Azure, vLLM, SGLang, DeepSeek, etc.) by providing `--base_url`, `--api_key`, and `--model_name`:
221
+
222
+ ```bash
223
+ python prompt_agent.py \
224
+ --backend api \
225
+ --base_url https://api.openai.com/v1 \
226
+ --api_key $OPENAI_API_KEY \
227
+ --model_name deepseek-v4-pro \
228
+ --prompt "李白的静夜思写在古墙上"
229
+ ```
230
+
231
+ ## Usage
232
+
233
+ A CUDA-capable GPU is required for inference. The examples below use the **undistilled** model (`--model_type full`); see the last subsection for running the same tasks with the **distilled** model (`--model_type dev`).
234
+
235
+ ### 1. Text-to-Image Generation
236
+ Generate an image from a text prompt:
237
+
238
+ ```bash
239
+ python inference.py \
240
+ --model_path /path/to/HiDream-O1-Image \
241
+ --prompt "medium shot, eye-level, front view. A woman is seated in an ornate bedroom, illuminated by candlelight, with a calm and composed expression. The subject is a young woman with fair skin, light brown hair styled in an updo with loose tendrils framing her face, and blue eyes. She wears a cream-colored satin robe with delicate floral embroidery and lace trim along the neckline. Her ears are adorned with pearl drop earrings. She is seated on a bed with a dark, intricately carved wooden headboard. To her left, a wooden nightstand holds three lit white candles and a candelabra with multiple lit candles in the background. The bed is covered with patterned pillows and a dark, textured blanket. The walls are paneled with dark wood and feature a large, ornate tapestry with muted earth tones. The lighting creates soft highlights on her face and robe, with warm shadows cast across the room." \
242
+ --output_image results/t2i.png \
243
+ --height 2048 \
244
+ --width 2048
245
+ ```
246
+
247
+ ### 2. Instruction-Based Image Editing
248
+ Provide a single reference image and an editing instruction:
249
+
250
+ ```bash
251
+ python inference.py \
252
+ --model_path /path/to/HiDream-O1-Image \
253
+ --prompt "remove the earphones" \
254
+ --ref_images assets/edit/test.jpg \
255
+ --output_image results/edit.png \
256
+ --keep_original_aspect
257
+ ```
258
+
259
+ ### 3. Multi-Reference Subject-Driven Personalization
260
+ Provide two or more reference images that define the subject(s), and a prompt that places them in a new scene:
261
+
262
+ ```bash
263
+ python inference.py \
264
+ --model_path /path/to/HiDream-O1-Image \
265
+ --shift 1 \
266
+ --prompt "A young boy with blonde hair stands on steps wearing light blue jeans, a white t-shirt with logo, and blue and white sneakers. He wears a brown cord necklace with beads, a black wristwatch with digital display, and carries a yellow fanny pack with white zipper. In his hand is a red boxing glove with white top, a teal plastic toy car, and a plastic toy figure of Captain America. He wears a straw hat with cream band. Natural light illuminates the scene." \
267
+ --ref_images assets/IP/1.jpg assets/IP/2.jpg assets/IP/3.jpg assets/IP/4.jpg assets/IP/5.jpg assets/IP/6.jpg assets/IP/7.jpg assets/IP/8.jpg assets/IP/9.jpg assets/IP/10.jpg \
268
+ --output_image results/subject.png
269
+ ```
270
+
271
+ ### 4. Multi-Reference Subject-Driven Personalization with Skeleton
272
+ ```bash
273
+ python inference.py \
274
+ --model_path /path/to/HiDream-O1-Image \
275
+ --shift 1 \
276
+ --seed 42 \
277
+ --prompt "Create a realistic try-on image of the person wearing the provided clothing." \
278
+ --ref_images assets/IP_skeleton/0.face.jpg assets/IP_skeleton/0.bg.jpg assets/IP_skeleton/0.openpose.jpg assets/IP_skeleton/0.part_1.jpg assets/IP_skeleton/0.part_2.jpg assets/IP_skeleton/0.part_3.jpg \
279
+ --output_image results/subject.png
280
+ ```
281
+
282
+ ### 5. Multi-Reference Subject-Driven Personalization with Layout
283
+ ```bash
284
+ python inference.py \
285
+ --model_path /path/to/HiDream-O1-Image \
286
+ --shift 1 \
287
+ --seed 42 \
288
+ --prompt "City council members pose with relaxed smiles on a sunlit terrace, warm approachable mood, golden hour, cinematic soft glow." \
289
+ --ref_images assets/IP_layout/0.jpg assets/IP_layout/1.jpg \
290
+ --layout_bboxes "[[0.20507812, 0.43945312, 0.48828125, 0.7421875 ], [0.57617188, 0.80078125, 0.08789062, 0.34179688]]" \
291
+ --output_image results/ip_layout.png
292
+ ```
293
+
294
+ ### 6. Running with the Dev Model
295
+ All three tasks above can be run with the **Dev** model by switching `--model_path` to the Dev checkpoint and setting `--model_type dev`. For example:
296
+
297
+ ```bash
298
+ python inference.py \
299
+ --model_path /path/to/HiDream-O1-Image-Dev \
300
+ --prompt "A dog holds a sign that says \"HiDream-O1-Image release.\"" \
301
+ --output_image results/t2i_dev.png \
302
+ --model_type dev
303
+ ```
304
+
305
+ For **editing** tasks (exactly one reference image), the Dev model defaults to the `flow_match` scheduler. `flow_match` is recommended for editing tasks. Pass `--editing_scheduler flash` to use the flash scheduler instead. This flag has no effect on the `full` model or on non-editing tasks.
306
+
307
+ ### Command Line Arguments
308
+
309
+ - `--model_path`: Path to the complete HuggingFace model directory (undistilled or distilled).
310
+ - `--prompt`: Text prompt for the generation or editing task.
311
+ - `--ref_images`: Paths to one or more reference images (optional; space-separated).
312
+ - `--output_image`: Path to save the generated image (default: `output.png`).
313
+ - `--height` / `--width`: Output image dimensions (default: `2048` × `2048`; values snap to valid resolutions internally).
314
+ - `--model_type`: `full` or `dev` (default: `full`). Selects the inference recipe:
315
+ - `full`: 50 steps, guidance scale `5.0`, shift `3.0`, default scheduler.
316
+ - `dev`: 28 steps, guidance scale `0.0`, shift `1.0`, flash scheduler with predefined timesteps. For editing tasks (exactly one reference image), the default scheduler is `flow_match` instead — see `--editing_scheduler`.
317
+ - `--seed`: Random seed (default: `32`).
318
+ - `--guidance_scale`: Guidance scale (default: `5.0`). Only effective when `--model_type` is `full`.
319
+ - `--noise_scale_start`, `--noise_scale_end`: Control the scale of the noise injected by the scheduler at each denoising step; the per-step scale linearly interpolates from `noise_scale_start` (first step) to `noise_scale_end` (last step). See `models/pipeline.py:313` (initial noise) and `models/pipeline.py:323-326` (per-step linear interpolation). Defaults: `7.5`, `7.5`.
320
+ - `--noise_clip_std`: Per-step clipping threshold (in units of the injected noise's standard deviation) applied to the noise added during scheduler stepping. See `models/flash_scheduler.py:350-354`. Default: `2.5`.
321
+ - `--editing_scheduler`: Scheduler to use for editing tasks (exactly one reference image) when `--model_type dev`. Choices: `flow_match` (default) or `flash`. Ignored for the `full` model and for non-editing tasks.
322
+ - `--keep_original_aspect`: When exactly one reference image is provided, resize it with `max_size=2048` and use its dimensions for the target image (preserves the reference's aspect ratio) if `True`.
323
+
324
+ ## Web Demo
325
+
326
+ `app.py` is a single-file Flask web UI (with HTML / CSS / JS embedded inline) that exposes all generation modes. It also integrates the Reasoning-Driven Prompt Agent.
327
+
328
+ ### Starting the server
329
+
330
+ ```bash
331
+ python app.py \
332
+ --model_path /path/to/HiDream-O1-Image \
333
+ --host 0.0.0.0 \
334
+ --port 7860
335
+ ```
336
+
337
+ Then open `http://localhost:7860` in your browser.
338
+
339
+ ### Command-line arguments
340
+
341
+ | Argument | Default | Description |
342
+ | :--- | :--- | :--- |
343
+ | `--model_path` | `$HIDREAM_MODEL_PATH` | Path to the checkpoint directory (`HiDream-O1-Image` or `HiDream-O1-Image-Dev`). |
344
+ | `--model_type` | `full` | `full` (50-step) or `dev` (28-step). |
345
+ | `--host` | `0.0.0.0` | Bind address for the Flask server. |
346
+ | `--port` | `7860` | Port for the Flask server. |
347
+
348
+ All four CLI arguments above can also be set via environment variables (see `.env.example`): `HIDREAM_MODEL_PATH`, `HIDREAM_MODEL_TYPE`, `HIDREAM_HOST`, and `HIDREAM_PORT`.
349
+
350
+ The Prompt Agent panel in the Web Demo reads additional environment variables from `.env`:
351
+
352
+ | Env Var | Used by | Description |
353
+ | :--- | :--- | :--- |
354
+ | `HIDREAM_AGENT_MODEL` | Local · Gemma backend | Path or HF repo id of the local Gemma weights. |
355
+ | `OPENAI_BASE_URL` | OpenAI-compatible API backend | Default base URL pre-filled in the UI. |
356
+ | `OPENAI_API_KEY` | OpenAI-compatible API backend | Default API key pre-filled in the UI. |
357
+ | `OPENAI_MODEL` | OpenAI-compatible API backend | Default model name pre-filled in the UI. |
358
+
359
+ ### Prompt Agent in the UI
360
+
361
+ The sidebar contains a Prompt Agent panel that calls the same Reasoning-Driven Prompt Agent used by `prompt_agent.py`. Select either the *OpenAI-compatible API* backend (any endpoint, key, and model name) or the *Local · Gemma* backend (set `HIDREAM_AGENT_MODEL` in `.env` or the environment to point to your local Gemma-4-31B-it weights).
362
+
363
+ ### Editing Scheduler (Dev model only)
364
+
365
+ When the server is launched with `--model_type dev`, the **Edit** tab exposes a *Scheduler* dropdown with two options: `flow_match` (default) and `flash`. The selector is hidden for the `full` model and for the Text → Image / Subject tabs, where the scheduler is fixed.
366
+
367
+ ## License
368
+ The code in this repository and the HiDream-O1-Image models are licensed under MIT License.
369
+
370
+ ## Citation
371
+
372
+ ```bibtex
373
+ @article{hidreamolimage,
374
+ title={HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer},
375
+ author={Cai, Qi and Chen, Jingwen and Gao, Chengmin and Gong, Zijian and Li, Yehao and Mei, Tao and Pan, Yingwei and Peng, Yi and Qiu, Zhaofan and Yao, Ting and Yu, Kai and Zhang, Yiheng and others},
376
+ journal={arXiv preprint arXiv:2605.11061},
377
+ year={2026}
378
+ }
379
+ ```
assets/IP.webp ADDED

Git LFS Details

  • SHA256: 9dc8f61b5e7cb68c2c82a82f930234adec0d9214f45d827f67cd073d4665d3e2
  • Pointer size: 132 Bytes
  • Size of remote file: 2.58 MB
assets/IP_2.jpg ADDED

Git LFS Details

  • SHA256: d62ab82d69046ecd423151096628a58e961bc44a264040aa1aa893fb5aab114a
  • Pointer size: 132 Bytes
  • Size of remote file: 1.27 MB
assets/general.webp ADDED

Git LFS Details

  • SHA256: 32a93bb7f0aa2792216bb4353176ee2e3fd574771448fcbae097a4f82db41fdd
  • Pointer size: 132 Bytes
  • Size of remote file: 5.57 MB
assets/leaderboard.png ADDED

Git LFS Details

  • SHA256: 4a5c034b0956cbbbec1f254f66bc7a71cdc9b37b1514042964cd5df4e5d14b44
  • Pointer size: 131 Bytes
  • Size of remote file: 773 kB
assets/text-layout.webp ADDED

Git LFS Details

  • SHA256: f12b57ab352811f259134a75aec3befb38ec956684474184d5f3b1aac2959184
  • Pointer size: 132 Bytes
  • Size of remote file: 5.54 MB
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
3
+ }
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 151655,
6
+ "model_type": "qwen3_vl",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 151643,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 151645,
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 12288,
18
+ "max_position_embeddings": 262144,
19
+ "model_type": "qwen3_vl_text",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 36,
22
+ "num_key_value_heads": 8,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": {
25
+ "mrope_interleaved": true,
26
+ "mrope_section": [
27
+ 24,
28
+ 20,
29
+ 20
30
+ ],
31
+ "rope_type": "default"
32
+ },
33
+ "rope_theta": 5000000,
34
+ "use_cache": true,
35
+ "vocab_size": 151936
36
+ },
37
+ "tie_word_embeddings": false,
38
+ "transformers_version": "4.57.0.dev0",
39
+ "video_token_id": 151656,
40
+ "vision_config": {
41
+ "deepstack_visual_indexes": [
42
+ 8,
43
+ 16,
44
+ 24
45
+ ],
46
+ "depth": 27,
47
+ "hidden_act": "gelu_pytorch_tanh",
48
+ "hidden_size": 1152,
49
+ "in_channels": 3,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 4304,
52
+ "model_type": "qwen3_vl",
53
+ "num_heads": 16,
54
+ "num_position_embeddings": 2304,
55
+ "out_hidden_size": 4096,
56
+ "patch_size": 16,
57
+ "spatial_merge_size": 2,
58
+ "temporal_patch_size": 2
59
+ },
60
+ "vision_end_token_id": 151653,
61
+ "vision_start_token_id": 151652
62
+ }
configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"framework": "pytorch", "task": "text-generation", "allow_remote": true}
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "pad_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "top_k": 20,
10
+ "top_p": 0.8,
11
+ "repetition_penalty": 1.0,
12
+ "temperature": 0.7,
13
+ "transformers_version": "4.56.0"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7be4c6ec2e15a16007f892b297ce85ecbe69dcaf39bc6271f3fb2665e9975ba
3
+ size 2481363944
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a01197ac2f1bf452483f0d8d34fd26e3bc506a43016f1bf83e29623801dc63e7
3
+ size 2416029160
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a2eb1c288b27ca020e03d9447f7a86412423dd356252844141e66e92854ab4
3
+ size 2416029184
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04be73ed3d0ec35e64c8217cb4f62c5c02f3a0e70a41334e1643ae493cd8ea62
3
+ size 2499933248
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa37d9fe1a98bc064afab08ce7ce860701673cbeea0e9e0f7bbfb93f403e434
3
+ size 2416029232
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b7627cf85081933a6aa7097fd209e8ce0d40128452c761d0fce11b8b8c8e46
3
+ size 2416029216
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc2794b4bf16e25a3defac265458ee1e96e12db3eea5dc2eca8694dc73ca86e7
3
+ size 1719794696
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb20adba426528634bfb1cf99b5794a2c3d3316010416a98074725050cbbd663
3
+ size 1244659840
model.safetensors.index.json ADDED
@@ -0,0 +1,767 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8804887792,
4
+ "total_size": 17609775584
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00008-of-00008.safetensors",
8
+ "model.final_layer2.linear.bias": "model-00007-of-00008.safetensors",
9
+ "model.final_layer2.linear.weight": "model-00007-of-00008.safetensors",
10
+ "model.language_model.embed_tokens.weight": "model-00001-of-00008.safetensors",
11
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00008.safetensors",
12
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
13
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
14
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
15
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
16
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
17
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
18
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
19
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
20
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
21
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
22
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors",
23
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
24
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
25
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
26
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
27
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
28
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
29
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
30
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
31
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
32
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
33
+ "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
34
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
35
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
36
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
37
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
38
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
39
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
40
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
41
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
42
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
43
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
44
+ "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
45
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
46
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
47
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
48
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
49
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
50
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
51
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
52
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
53
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
54
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
55
+ "model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
56
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
57
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
58
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
59
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
60
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
61
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
62
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
63
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
64
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
65
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
66
+ "model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
67
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
68
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
69
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
70
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
71
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
72
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
73
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
74
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
75
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
76
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
77
+ "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
78
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
79
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
80
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
81
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
82
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
83
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
84
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
85
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
86
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
87
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
88
+ "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
89
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
90
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
91
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
92
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
93
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
94
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
95
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
96
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
97
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
98
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
99
+ "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
100
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
101
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
102
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
103
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
104
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
105
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
106
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
107
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
108
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
109
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
110
+ "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
111
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
112
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
113
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
114
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
115
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
116
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
117
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
118
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
119
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
120
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
121
+ "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
122
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
123
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
124
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
125
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
126
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
127
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
128
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
129
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
130
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
131
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
132
+ "model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
133
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
134
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
135
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
136
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
137
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
138
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
139
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
140
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
141
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
142
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
143
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
144
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
145
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
146
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
147
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
148
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
149
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
150
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
151
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
152
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
153
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
154
+ "model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
155
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
156
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
157
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
158
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
159
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
160
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
161
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
162
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
163
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
164
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
165
+ "model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
166
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
167
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
168
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
169
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
170
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
171
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
172
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
173
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
174
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
175
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
176
+ "model.language_model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
177
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
178
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
179
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
180
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
181
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
182
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
183
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
184
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
185
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
186
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
187
+ "model.language_model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
188
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
189
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
190
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
191
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
192
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
193
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
194
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
195
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
196
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
197
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
198
+ "model.language_model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
199
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
200
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
201
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
202
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
203
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
204
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
205
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
206
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
207
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
208
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
209
+ "model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
210
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
211
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
212
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
213
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
214
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
215
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
216
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
217
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
218
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
219
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
220
+ "model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
221
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
222
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
223
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
224
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
225
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
226
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
227
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
228
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
229
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
230
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
231
+ "model.language_model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
232
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
233
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
234
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
235
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
236
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
237
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
238
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
239
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
240
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
241
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
242
+ "model.language_model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
243
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
244
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
245
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
246
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
247
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
248
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
249
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
250
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
251
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
252
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
253
+ "model.language_model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
254
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
255
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
256
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
257
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
258
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
259
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
260
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
261
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
262
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
263
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
264
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
265
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
266
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
267
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
268
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
269
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
270
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
271
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
272
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
273
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
274
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
275
+ "model.language_model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
276
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
277
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
278
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
279
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
280
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
281
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
282
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
283
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
284
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
285
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
286
+ "model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
287
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
288
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
289
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
290
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
291
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
292
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
293
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
294
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
295
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
296
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
297
+ "model.language_model.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors",
298
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
299
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
300
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
301
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
302
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
303
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
304
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
305
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
306
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
307
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
308
+ "model.language_model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors",
309
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
310
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
311
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
312
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
313
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
314
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
315
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
316
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
317
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
318
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
319
+ "model.language_model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
320
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
321
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
322
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
323
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
324
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
325
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
326
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
327
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
328
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
329
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
330
+ "model.language_model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
331
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
332
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
333
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
334
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
335
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
336
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
337
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
338
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
339
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
340
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
341
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
342
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
343
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
344
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
345
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
346
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
347
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
348
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
349
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
350
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
351
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
352
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
353
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
354
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
355
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
356
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
357
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
358
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
359
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
360
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
361
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
362
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
363
+ "model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00008.safetensors",
364
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
365
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
366
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
367
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
368
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
369
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
370
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
371
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
372
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
373
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
374
+ "model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
375
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
376
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
377
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
378
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
379
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
380
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
381
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
382
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
383
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
384
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
385
+ "model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
386
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
387
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
388
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
389
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
390
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
391
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
392
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
393
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
394
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
395
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
396
+ "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
397
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
398
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
399
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
400
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
401
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
402
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
403
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
404
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
405
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
406
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
407
+ "model.language_model.norm.weight": "model-00007-of-00008.safetensors",
408
+ "model.t_embedder1.mlp.0.bias": "model-00007-of-00008.safetensors",
409
+ "model.t_embedder1.mlp.0.weight": "model-00007-of-00008.safetensors",
410
+ "model.t_embedder1.mlp.2.bias": "model-00007-of-00008.safetensors",
411
+ "model.t_embedder1.mlp.2.weight": "model-00007-of-00008.safetensors",
412
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00008.safetensors",
413
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00008.safetensors",
414
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00008.safetensors",
415
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00008.safetensors",
416
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
417
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
418
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
419
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
420
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00008.safetensors",
421
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00008.safetensors",
422
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00008.safetensors",
423
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00008.safetensors",
424
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00008.safetensors",
425
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00008.safetensors",
426
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00008.safetensors",
427
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00008.safetensors",
428
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
429
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
430
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
431
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
432
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00008.safetensors",
433
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00008.safetensors",
434
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00008.safetensors",
435
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00008.safetensors",
436
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00008.safetensors",
437
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00008.safetensors",
438
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00008.safetensors",
439
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00008.safetensors",
440
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
441
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
442
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
443
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
444
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00008.safetensors",
445
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00008.safetensors",
446
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00008.safetensors",
447
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00008.safetensors",
448
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00008.safetensors",
449
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00008.safetensors",
450
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00008.safetensors",
451
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00008.safetensors",
452
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
453
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
454
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
455
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
456
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00008.safetensors",
457
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00008.safetensors",
458
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00008.safetensors",
459
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00008.safetensors",
460
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00008.safetensors",
461
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00008.safetensors",
462
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00008.safetensors",
463
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00008.safetensors",
464
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
465
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
466
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
467
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
468
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00008.safetensors",
469
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00008.safetensors",
470
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00008.safetensors",
471
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00008.safetensors",
472
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00008.safetensors",
473
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00008.safetensors",
474
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00008.safetensors",
475
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00008.safetensors",
476
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
477
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
478
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
479
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
480
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00008.safetensors",
481
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00008.safetensors",
482
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00008.safetensors",
483
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00008.safetensors",
484
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00008.safetensors",
485
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00008.safetensors",
486
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00008.safetensors",
487
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00008.safetensors",
488
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
489
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
490
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
491
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
492
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00008.safetensors",
493
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00008.safetensors",
494
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00008.safetensors",
495
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00008.safetensors",
496
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00008.safetensors",
497
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00008.safetensors",
498
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00008.safetensors",
499
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00008.safetensors",
500
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
501
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
502
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
503
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
504
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00008.safetensors",
505
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00008.safetensors",
506
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00008.safetensors",
507
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00008.safetensors",
508
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00008.safetensors",
509
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00008.safetensors",
510
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00008.safetensors",
511
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00008.safetensors",
512
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
513
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
514
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
515
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
516
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00008.safetensors",
517
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00008.safetensors",
518
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00008.safetensors",
519
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00008.safetensors",
520
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00008.safetensors",
521
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00008.safetensors",
522
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00008.safetensors",
523
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00008.safetensors",
524
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
525
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
526
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
527
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
528
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00008.safetensors",
529
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00008.safetensors",
530
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00008.safetensors",
531
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00008.safetensors",
532
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00008.safetensors",
533
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00008.safetensors",
534
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00008.safetensors",
535
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00008.safetensors",
536
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
537
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
538
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
539
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
540
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00008.safetensors",
541
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00008.safetensors",
542
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00008.safetensors",
543
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00008.safetensors",
544
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00008.safetensors",
545
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00008.safetensors",
546
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00008.safetensors",
547
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00008.safetensors",
548
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
549
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
550
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
551
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
552
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00008.safetensors",
553
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00008.safetensors",
554
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00008.safetensors",
555
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00008.safetensors",
556
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00008.safetensors",
557
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00008.safetensors",
558
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00008.safetensors",
559
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00008.safetensors",
560
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
561
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
562
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
563
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
564
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00008.safetensors",
565
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00008.safetensors",
566
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00008.safetensors",
567
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00008.safetensors",
568
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00008.safetensors",
569
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00008.safetensors",
570
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00008.safetensors",
571
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00008.safetensors",
572
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
573
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
574
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
575
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
576
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00008.safetensors",
577
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00008.safetensors",
578
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00008.safetensors",
579
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00008.safetensors",
580
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00008.safetensors",
581
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00008.safetensors",
582
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00008.safetensors",
583
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00008.safetensors",
584
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
585
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
586
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
587
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
588
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00008.safetensors",
589
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00008.safetensors",
590
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00008.safetensors",
591
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00008.safetensors",
592
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00008.safetensors",
593
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00008.safetensors",
594
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00008.safetensors",
595
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00008.safetensors",
596
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
597
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
598
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
599
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
600
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00008.safetensors",
601
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00008.safetensors",
602
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00008.safetensors",
603
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00008.safetensors",
604
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00008.safetensors",
605
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00008.safetensors",
606
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00008.safetensors",
607
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00008.safetensors",
608
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
609
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
610
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
611
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
612
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00008.safetensors",
613
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00008.safetensors",
614
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00008.safetensors",
615
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00008.safetensors",
616
+ "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00008.safetensors",
617
+ "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00008.safetensors",
618
+ "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00008.safetensors",
619
+ "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00008.safetensors",
620
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
621
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
622
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
623
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
624
+ "model.visual.blocks.24.norm1.bias": "model-00001-of-00008.safetensors",
625
+ "model.visual.blocks.24.norm1.weight": "model-00001-of-00008.safetensors",
626
+ "model.visual.blocks.24.norm2.bias": "model-00001-of-00008.safetensors",
627
+ "model.visual.blocks.24.norm2.weight": "model-00001-of-00008.safetensors",
628
+ "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00008.safetensors",
629
+ "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00008.safetensors",
630
+ "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00008.safetensors",
631
+ "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00008.safetensors",
632
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
633
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
634
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
635
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
636
+ "model.visual.blocks.25.norm1.bias": "model-00001-of-00008.safetensors",
637
+ "model.visual.blocks.25.norm1.weight": "model-00001-of-00008.safetensors",
638
+ "model.visual.blocks.25.norm2.bias": "model-00001-of-00008.safetensors",
639
+ "model.visual.blocks.25.norm2.weight": "model-00001-of-00008.safetensors",
640
+ "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00008.safetensors",
641
+ "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00008.safetensors",
642
+ "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00008.safetensors",
643
+ "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00008.safetensors",
644
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
645
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
646
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
647
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
648
+ "model.visual.blocks.26.norm1.bias": "model-00001-of-00008.safetensors",
649
+ "model.visual.blocks.26.norm1.weight": "model-00001-of-00008.safetensors",
650
+ "model.visual.blocks.26.norm2.bias": "model-00001-of-00008.safetensors",
651
+ "model.visual.blocks.26.norm2.weight": "model-00001-of-00008.safetensors",
652
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00008.safetensors",
653
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00008.safetensors",
654
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00008.safetensors",
655
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00008.safetensors",
656
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
657
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
658
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
659
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
660
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00008.safetensors",
661
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00008.safetensors",
662
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00008.safetensors",
663
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00008.safetensors",
664
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00008.safetensors",
665
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00008.safetensors",
666
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00008.safetensors",
667
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00008.safetensors",
668
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
669
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
670
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
671
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
672
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00008.safetensors",
673
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00008.safetensors",
674
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00008.safetensors",
675
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00008.safetensors",
676
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00008.safetensors",
677
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00008.safetensors",
678
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00008.safetensors",
679
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00008.safetensors",
680
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
681
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
682
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
683
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
684
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00008.safetensors",
685
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00008.safetensors",
686
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00008.safetensors",
687
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00008.safetensors",
688
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00008.safetensors",
689
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00008.safetensors",
690
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00008.safetensors",
691
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00008.safetensors",
692
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
693
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
694
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
695
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
696
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00008.safetensors",
697
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00008.safetensors",
698
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00008.safetensors",
699
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00008.safetensors",
700
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00008.safetensors",
701
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00008.safetensors",
702
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00008.safetensors",
703
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00008.safetensors",
704
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
705
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
706
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
707
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
708
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00008.safetensors",
709
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00008.safetensors",
710
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00008.safetensors",
711
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00008.safetensors",
712
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00008.safetensors",
713
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00008.safetensors",
714
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00008.safetensors",
715
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00008.safetensors",
716
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
717
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
718
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
719
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
720
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00008.safetensors",
721
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00008.safetensors",
722
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00008.safetensors",
723
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00008.safetensors",
724
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00008.safetensors",
725
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00008.safetensors",
726
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00008.safetensors",
727
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00008.safetensors",
728
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00008.safetensors",
729
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00008.safetensors",
730
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00008.safetensors",
731
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00008.safetensors",
732
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00008.safetensors",
733
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00008.safetensors",
734
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00008.safetensors",
735
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00008.safetensors",
736
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00008.safetensors",
737
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00008.safetensors",
738
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00008.safetensors",
739
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00008.safetensors",
740
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00008.safetensors",
741
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00008.safetensors",
742
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00008.safetensors",
743
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00008.safetensors",
744
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00008.safetensors",
745
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00008.safetensors",
746
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00008.safetensors",
747
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00008.safetensors",
748
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00008.safetensors",
749
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00008.safetensors",
750
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00008.safetensors",
751
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00008.safetensors",
752
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00008.safetensors",
753
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00008.safetensors",
754
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00008.safetensors",
755
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00008.safetensors",
756
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00008.safetensors",
757
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00008.safetensors",
758
+ "model.visual.merger.norm.bias": "model-00001-of-00008.safetensors",
759
+ "model.visual.merger.norm.weight": "model-00001-of-00008.safetensors",
760
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00008.safetensors",
761
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00008.safetensors",
762
+ "model.visual.pos_embed.weight": "model-00001-of-00008.safetensors",
763
+ "model.x_embedder.proj1.weight": "model-00007-of-00008.safetensors",
764
+ "model.x_embedder.proj2.bias": "model-00007-of-00008.safetensors",
765
+ "model.x_embedder.proj2.weight": "model-00007-of-00008.safetensors"
766
+ }
767
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>",
228
+ "<|boi_token|>",
229
+ "<|bor_token|>",
230
+ "<|eor_token|>",
231
+ "<|bot_token|>",
232
+ "<|tms_token|>"
233
+ ],
234
+ "bos_token": null,
235
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
236
+ "clean_up_tokenization_spaces": false,
237
+ "eos_token": "<|im_end|>",
238
+ "errors": "replace",
239
+ "model_max_length": 262144,
240
+ "pad_token": "<|endoftext|>",
241
+ "split_special_tokens": false,
242
+ "tokenizer_class": "Qwen2Tokenizer",
243
+ "unk_token": null
244
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff