Upload HiDream-O1-Image-SDNQ-4bit model files
Browse files- .gitattributes +5 -0
- .mdl +0 -0
- .msc +0 -0
- .mv +1 -0
- README.md +348 -0
- assets/IP.webp +3 -0
- assets/IP_2.jpg +3 -0
- assets/general.webp +3 -0
- assets/leaderboard.png +3 -0
- assets/text-layout.webp +3 -0
- chat_template.json +3 -0
- config.json +62 -0
- configuration.json +1 -0
- generation_config.json +14 -0
- language_model/language_model.safetensors +3 -0
- lm_head/lm_head.safetensors +3 -0
- merges.txt +0 -0
- model.safetensors.index.json +583 -0
- preprocessor_config.json +21 -0
- tokenizer.json +0 -0
- tokenizer_config.json +244 -0
- video_preprocessor_config.json +21 -0
- visual_encoder/visual_encoder.safetensors +3 -0
- 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 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
pipeline_tag: image-text-to-image
|
| 4 |
+
library_name: transformers
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# HiDream-O1-Image
|
| 8 |
+
|
| 9 |
+
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.
|
| 10 |
+
|
| 11 |
+
## Project Updates
|
| 12 |
+
- 🛠️ **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)
|
| 13 |
+
- 🤗 **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).
|
| 14 |
+
- 📕 **May 10, 2026:** Our **technical report** is now available — [📑 HiDream-O1-Image.pdf](https://github.com/HiDream-ai/HiDream-O1-Image/blob/main/assets/HiDream-O1-Image.pdf).
|
| 15 |
+
- 🚀 **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.
|
| 16 |
+
|
| 17 |
+
> **HiDream-O1-Image (codename: Peanut) 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 (2026-5-5).**
|
| 18 |
+
|
| 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 |
+
## Models
|
| 48 |
+
|
| 49 |
+
| Name | Script | Inference Steps | HuggingFace Repo |
|
| 50 |
+
| :--- | :--- | :---: | :--- |
|
| 51 |
+
| HiDream-O1-Image | `inference.py` | 50 | [🤗 HiDream-O1-Image](https://huggingface.co/HiDream-ai/HiDream-O1-Image) |
|
| 52 |
+
| HiDream-O1-Image-Dev | `inference.py` | 28 | [🤗 HiDream-O1-Image-Dev](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev) |
|
| 53 |
+
| Prompt Agent | `prompt_agent.py` | — | [🤗 google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it) |
|
| 54 |
+
| Web Demo | `app.py` | — | — |
|
| 55 |
+
|
| 56 |
+
## Evaluation
|
| 57 |
+
|
| 58 |
+
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.
|
| 59 |
+
|
| 60 |
+
<details open>
|
| 61 |
+
<summary><b>GenEval</b> — compositional generation</summary>
|
| 62 |
+
|
| 63 |
+
| Model | #Params | Single-Obj | Two-Obj | Count | Color | Position | Attr | Overall |
|
| 64 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 65 |
+
| Nano Banana 2.0 | – | 1.00 | 0.96 | 0.71 | 0.84 | 0.86 | 0.65 | 0.83 |
|
| 66 |
+
| Seedream-4.0 | – | 1.00 | 0.92 | 0.71 | 0.93 | 0.78 | 0.68 | 0.84 |
|
| 67 |
+
| GPT Image 1 [High] | – | 0.99 | 0.92 | 0.85 | 0.92 | 0.75 | 0.61 | 0.84 |
|
| 68 |
+
| GPT Image 2 | – | 0.99 | 0.98 | 0.85 | 0.93 | 0.85 | 0.77 | 0.89 |
|
| 69 |
+
| PixArt | 4.3B + 0.6B | 0.98 | 0.50 | 0.44 | 0.80 | 0.08 | 0.07 | 0.48 |
|
| 70 |
+
| Show-o | 1.3B | 0.95 | 0.52 | 0.49 | 0.82 | 0.11 | 0.28 | 0.53 |
|
| 71 |
+
| Emu3-Gen | 8B | 0.98 | 0.71 | 0.34 | 0.81 | 0.17 | 0.21 | 0.54 |
|
| 72 |
+
| SD3-Medium | 5.5B + 2B | 0.98 | 0.74 | 0.63 | 0.67 | 0.34 | 0.36 | 0.62 |
|
| 73 |
+
| JanusFlow | 1.3B | 0.97 | 0.59 | 0.45 | 0.83 | 0.53 | 0.42 | 0.63 |
|
| 74 |
+
| FLUX.1 [Dev] | 4.8B + 12B | 0.98 | 0.81 | 0.74 | 0.79 | 0.22 | 0.45 | 0.66 |
|
| 75 |
+
| SD3.5 Large | 5.5B + 8.1B | 0.98 | 0.89 | 0.73 | 0.83 | 0.34 | 0.47 | 0.71 |
|
| 76 |
+
| Janus-Pro-7B | 7B | 0.99 | 0.89 | 0.59 | 0.90 | 0.79 | 0.66 | 0.80 |
|
| 77 |
+
| Z-Image-Turbo | 4B + 6B | 1.00 | 0.95 | 0.77 | 0.89 | 0.65 | 0.68 | 0.82 |
|
| 78 |
+
| FLUX.2 [Dev] | 24B + 32B | 1.00 | 0.99 | 0.79 | 0.93 | 0.73 | 0.78 | 0.87 |
|
| 79 |
+
| Qwen-Image | 7B + 20B | 0.99 | 0.92 | 0.89 | 0.88 | 0.76 | 0.77 | 0.87 |
|
| 80 |
+
| **HiDream-O1-Image** | 8B | 1.00 | 0.99 | 0.79 | 0.89 | 0.93 | 0.78 | <u>0.90</u> |
|
| 81 |
+
| **HiDream-O1-Image-Pro** | 200B+ | 1.00 | 0.99 | 0.85 | 0.94 | 0.94 | 0.79 | **0.92** |
|
| 82 |
+
|
| 83 |
+
</details>
|
| 84 |
+
|
| 85 |
+
<details open>
|
| 86 |
+
<summary><b>DPG-Bench</b> — dense prompt alignment</summary>
|
| 87 |
+
|
| 88 |
+
| Model | #Params | Global | Entity | Attribute | Relation | Other | Overall |
|
| 89 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 90 |
+
| GPT Image 1 [High] | – | 88.89 | 88.94 | 89.84 | 92.63 | 90.96 | 85.15 |
|
| 91 |
+
| GPT Image 2 | – | 87.27 | 91.91 | 90.85 | 91.59 | 91.58 | 85.98 |
|
| 92 |
+
| Nano Banana 2.0 | – | 85.17 | 92.55 | 91.16 | 90.45 | 91.08 | 86.90 |
|
| 93 |
+
| Seedream-4.0 | – | 87.17 | 92.41 | 92.29 | 93.33 | 95.48 | 88.63 |
|
| 94 |
+
| SD v1.5 | 0.12B + 0.86B | 74.63 | 74.23 | 75.39 | 73.49 | 67.81 | 63.18 |
|
| 95 |
+
| PixArt | 4.3B + 0.6B | 74.97 | 79.32 | 78.60 | 82.57 | 76.96 | 71.11 |
|
| 96 |
+
| Lumina-Next | 2B + 2B | 82.82 | 88.65 | 86.44 | 80.53 | 81.82 | 74.63 |
|
| 97 |
+
| SDXL | 0.81B + 2.6B | 83.27 | 82.43 | 80.91 | 86.76 | 80.41 | 74.65 |
|
| 98 |
+
| Hunyuan-DiT | 4.8B + 1.5B | 84.59 | 80.59 | 88.01 | 74.36 | 86.41 | 78.87 |
|
| 99 |
+
| Emu3-Gen | 8B | 85.21 | 86.68 | 86.84 | 90.22 | 83.15 | 80.60 |
|
| 100 |
+
| DALL-E 3 | – | 90.97 | 89.61 | 88.39 | 90.58 | 89.83 | 83.50 |
|
| 101 |
+
| FLUX.1 [Dev] | 4.8B + 12B | 74.35 | 90.00 | 88.96 | 90.87 | 88.33 | 83.84 |
|
| 102 |
+
| SD3 Medium | 5.5B + 2B | 87.90 | 91.01 | 88.83 | 80.70 | 88.68 | 84.08 |
|
| 103 |
+
| Janus-Pro-7B | 7B | 86.90 | 88.90 | 89.40 | 89.32 | 89.48 | 84.19 |
|
| 104 |
+
| Z-Image-Turbo | 4B + 6B | 91.29 | 89.59 | 90.14 | 92.16 | 88.68 | 84.86 |
|
| 105 |
+
| HiDream-I1-Full | 13.5B + 17B | 76.44 | 90.22 | 89.48 | 93.74 | 91.83 | 85.89 |
|
| 106 |
+
| FLUX.2 [Dev] | 24B + 32B | 92.20 | 91.36 | 93.28 | 93.52 | 89.72 | 87.57 |
|
| 107 |
+
| Qwen-Image | 7B + 20B | 91.32 | 91.56 | 92.02 | 94.31 | 92.73 | 88.32 |
|
| 108 |
+
| **HiDream-O1-Image** | 8B | 95.15 | 92.32 | 93.74 | 92.88 | 90.25 | <u>89.83</u> |
|
| 109 |
+
| **HiDream-O1-Image-Pro** | 200B+ | 94.97 | 95.42 | 92.59 | 90.82 | 89.50 | **90.30** |
|
| 110 |
+
|
| 111 |
+
</details>
|
| 112 |
+
|
| 113 |
+
<details open>
|
| 114 |
+
<summary><b>HPSv3</b> — human preference across 12 categories</summary>
|
| 115 |
+
|
| 116 |
+
| Model | #Params | All | Characters | Arts | Design | Architecture | Animals | Natural Scenery | Transportation | Products | Plants | Food | Science | Others |
|
| 117 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 118 |
+
| 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 |
|
| 119 |
+
| 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 |
|
| 120 |
+
| 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 |
|
| 121 |
+
| 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 |
|
| 122 |
+
| 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 |
|
| 123 |
+
| 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 |
|
| 124 |
+
| **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 |
|
| 125 |
+
| **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 |
|
| 126 |
+
|
| 127 |
+
</details>
|
| 128 |
+
|
| 129 |
+
<details>
|
| 130 |
+
<summary><b>CVTG-2K</b> — complex visual text generation (click to expand)</summary>
|
| 131 |
+
|
| 132 |
+
| Model | #Params | 2 regions | 3 regions | 4 regions | 5 regions | Average | NED | CLIP Score |
|
| 133 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 134 |
+
| Nano Banana 2.0 | – | 0.7465 | 0.7720 | 0.8067 | 0.7980 | 0.7875 | 0.8945 | 0.7212 |
|
| 135 |
+
| GPT Image 1 [High] | – | 0.8779 | 0.8659 | 0.8731 | 0.8218 | 0.8569 | 0.9478 | 0.7982 |
|
| 136 |
+
| Seedream-4.0 | – | 0.8980 | 0.8949 | 0.9044 | 0.9015 | 0.9003 | 0.9511 | 0.8033 |
|
| 137 |
+
| GPT Image 2 | – | 0.8904 | 0.8887 | 0.9101 | 0.9044 | 0.9003 | 0.9515 | 0.7798 |
|
| 138 |
+
| TextDiffuser-2 | 0.12B + 0.9B | 0.5322 | 0.3255 | 0.1787 | 0.0809 | 0.2326 | 0.4353 | 0.6765 |
|
| 139 |
+
| RAG-Diffusion | 4.8B + 12B | 0.4388 | 0.3316 | 0.2116 | 0.1910 | 0.2648 | 0.4498 | 0.7797 |
|
| 140 |
+
| AnyText | 0.123B + 1.2B | 0.0513 | 0.1739 | 0.1948 | 0.2249 | 0.1804 | 0.4675 | 0.7432 |
|
| 141 |
+
| 3DIS | 0.81B + 2.6B | 0.4495 | 0.3959 | 0.3880 | 0.3303 | 0.3813 | 0.6505 | 0.7767 |
|
| 142 |
+
| FLUX.1 [Dev] | 4.8B + 12B | 0.6089 | 0.5531 | 0.4661 | 0.4316 | 0.4965 | 0.6879 | 0.7401 |
|
| 143 |
+
| SD3.5 Large | 5.5B + 8.1B | 0.7293 | 0.6825 | 0.6574 | 0.5940 | 0.6548 | 0.8470 | 0.7797 |
|
| 144 |
+
| TextCrafter | 7B + 20B | 0.7628 | 0.7628 | 0.7406 | 0.6977 | 0.7370 | 0.8679 | 0.7868 |
|
| 145 |
+
| Qwen-Image | 7B + 20B | 0.8370 | 0.8364 | 0.8313 | 0.8158 | 0.8288 | 0.9116 | 0.8017 |
|
| 146 |
+
| Z-Image-Turbo | 4B + 6B | 0.8872 | 0.8662 | 0.8628 | 0.8347 | 0.8585 | 0.9281 | 0.8048 |
|
| 147 |
+
| FLUX.2 [Dev] | 24B + 32B | 0.9261 | 0.8897 | 0.8995 | 0.8732 | 0.8926 | 0.9475 | <u>0.8104</u> |
|
| 148 |
+
| **HiDream-O1-Image** | 8B | 0.9085 | 0.9159 | 0.9216 | 0.9015 | <u>0.9128</u> | <u>0.9561</u> | 0.8076 |
|
| 149 |
+
| **HiDream-O1-Image-Pro** | 200B+ | 0.9133 | 0.9221 | 0.9365 | 0.9175 | **0.9222** | **0.9628** | **0.8349** |
|
| 150 |
+
|
| 151 |
+
</details>
|
| 152 |
+
|
| 153 |
+
<details>
|
| 154 |
+
<summary><b>LongText-Bench</b> — long-text rendering, EN & ZH (click to expand)</summary>
|
| 155 |
+
|
| 156 |
+
| Model | #Params | LongText-Bench-EN | LongText-Bench-ZH |
|
| 157 |
+
| :--- | :---: | :---: | :---: |
|
| 158 |
+
| Seedream-4.0 | – | 0.936 | 0.946 |
|
| 159 |
+
| GPT Image 1 [High] | – | 0.956 | 0.619 |
|
| 160 |
+
| GPT Image 2 | – | 0.960 | 0.961 |
|
| 161 |
+
| Nano Banana 2.0 | – | <u>0.980</u> | 0.965 |
|
| 162 |
+
| Janus-Pro-7B | 7B | 0.019 | 0.006 |
|
| 163 |
+
| BLIP3-o | 7B + 1.4B | 0.021 | 0.018 |
|
| 164 |
+
| Kolors 2.0 | – | 0.258 | 0.329 |
|
| 165 |
+
| BAGEL | 7B + 7B | 0.373 | 0.310 |
|
| 166 |
+
| OmniGen2 | 3B + 4B | 0.561 | 0.059 |
|
| 167 |
+
| X-Omni | 7B | 0.900 | 0.814 |
|
| 168 |
+
| HiDream-I1-Full | 13.5B + 17B | 0.543 | 0.024 |
|
| 169 |
+
| FLUX.1 [Dev] | 4.8B + 12B | 0.607 | 0.005 |
|
| 170 |
+
| Z-Image-Turbo | 4B + 6B | 0.917 | 0.926 |
|
| 171 |
+
| FLUX.2 [Dev] | 24B + 32B | 0.963 | 0.757 |
|
| 172 |
+
| Qwen-Image | 7B + 20B | 0.943 | 0.946 |
|
| 173 |
+
| **HiDream-O1-Image** | 8B | 0.979 | <u>0.978</u> |
|
| 174 |
+
| **HiDream-O1-Image-Pro** | 200B+ | **0.982** | **0.980** |
|
| 175 |
+
|
| 176 |
+
</details>
|
| 177 |
+
|
| 178 |
+
## Installation
|
| 179 |
+
|
| 180 |
+
1. Clone this repository:
|
| 181 |
+
```bash
|
| 182 |
+
git clone https://github.com/HiDream-ai/HiDream-O1-Image.git
|
| 183 |
+
cd HiDream-O1-Image
|
| 184 |
+
```
|
| 185 |
+
|
| 186 |
+
2. Install the required dependencies:
|
| 187 |
+
```bash
|
| 188 |
+
pip install -r requirements.txt
|
| 189 |
+
```
|
| 190 |
+
|
| 191 |
+
> **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 291 and change `"use_flash_attn": True` to `"use_flash_attn": False`** — otherwise inference will fail to import the kernel.
|
| 192 |
+
|
| 193 |
+
## Reasoning-Driven Prompt Agent
|
| 194 |
+
|
| 195 |
+
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`.
|
| 196 |
+
|
| 197 |
+
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.
|
| 198 |
+
|
| 199 |
+
### Option A — Local Backend (Gemma-4-31B-it)
|
| 200 |
+
|
| 201 |
+
1. Download the Gemma weights (requires accepting the Gemma license on HuggingFace):
|
| 202 |
+
```bash
|
| 203 |
+
huggingface-cli download google/gemma-4-31B-it --local-dir /path/to/gemma-4-31B-it
|
| 204 |
+
```
|
| 205 |
+
|
| 206 |
+
2. Run the refiner locally:
|
| 207 |
+
```bash
|
| 208 |
+
python prompt_agent.py \
|
| 209 |
+
--backend local \
|
| 210 |
+
--model_id /path/to/gemma-4-31B-it \
|
| 211 |
+
--prompt "李白的静夜思写在古墙上"
|
| 212 |
+
```
|
| 213 |
+
|
| 214 |
+
### Option B — External OpenAI-Compatible API
|
| 215 |
+
|
| 216 |
+
Use any OpenAI-compatible endpoint (OpenAI, Azure, vLLM, SGLang, DeepSeek, etc.) by providing `--base_url`, `--api_key`, and `--model_name`:
|
| 217 |
+
|
| 218 |
+
```bash
|
| 219 |
+
python prompt_agent.py \
|
| 220 |
+
--backend api \
|
| 221 |
+
--base_url https://api.openai.com/v1 \
|
| 222 |
+
--api_key $OPENAI_API_KEY \
|
| 223 |
+
--model_name deepseek-v4-pro \
|
| 224 |
+
--prompt "李白的静夜思写在古墙上"
|
| 225 |
+
```
|
| 226 |
+
|
| 227 |
+
## Usage
|
| 228 |
+
|
| 229 |
+
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`).
|
| 230 |
+
|
| 231 |
+
### 1. Text-to-Image Generation
|
| 232 |
+
Generate an image from a text prompt:
|
| 233 |
+
|
| 234 |
+
```bash
|
| 235 |
+
python inference.py \
|
| 236 |
+
--model_path /path/to/HiDream-O1-Image \
|
| 237 |
+
--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." \
|
| 238 |
+
--output_image results/t2i.png \
|
| 239 |
+
--height 2048 \
|
| 240 |
+
--width 2048
|
| 241 |
+
```
|
| 242 |
+
|
| 243 |
+
### 2. Instruction-Based Image Editing
|
| 244 |
+
Provide a single reference image and an editing instruction:
|
| 245 |
+
|
| 246 |
+
```bash
|
| 247 |
+
python inference.py \
|
| 248 |
+
--model_path /path/to/HiDream-O1-Image \
|
| 249 |
+
--prompt "remove the earphones" \
|
| 250 |
+
--ref_images assets/edit/test.jpg \
|
| 251 |
+
--output_image results/edit.png \
|
| 252 |
+
--keep_original_aspect
|
| 253 |
+
```
|
| 254 |
+
|
| 255 |
+
### 3. Multi-Reference Subject-Driven Personalization
|
| 256 |
+
Provide two or more reference images that define the subject(s), and a prompt that places them in a new scene:
|
| 257 |
+
|
| 258 |
+
```bash
|
| 259 |
+
python inference.py \
|
| 260 |
+
--model_path /path/to/HiDream-O1-Image \
|
| 261 |
+
--shift 1 \
|
| 262 |
+
--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." \
|
| 263 |
+
--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 \
|
| 264 |
+
--output_image results/subject.png
|
| 265 |
+
```
|
| 266 |
+
|
| 267 |
+
### 4. Multi-Reference Subject-Driven Personalization with Skeleton
|
| 268 |
+
```bash
|
| 269 |
+
python inference.py \
|
| 270 |
+
--model_path /path/to/HiDream-O1-Image \
|
| 271 |
+
--shift 1 \
|
| 272 |
+
--seed 42 \
|
| 273 |
+
--prompt "Create a realistic try-on image of the person wearing the provided clothing." \
|
| 274 |
+
--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 \
|
| 275 |
+
--output_image results/subject.png
|
| 276 |
+
```
|
| 277 |
+
|
| 278 |
+
### 5. Multi-Reference Subject-Driven Personalization with Layout
|
| 279 |
+
```bash
|
| 280 |
+
python inference.py \
|
| 281 |
+
--model_path /path/to/HiDream-O1-Image \
|
| 282 |
+
--shift 1 \
|
| 283 |
+
--seed 42 \
|
| 284 |
+
--prompt "City council members pose with relaxed smiles on a sunlit terrace, warm approachable mood, golden hour, cinematic soft glow." \
|
| 285 |
+
--ref_images assets/IP_layout/0.jpg assets/IP_layout/1.jpg \
|
| 286 |
+
--layout_bboxes "[[0.20507812, 0.43945312, 0.48828125, 0.7421875 ], [0.57617188, 0.80078125, 0.08789062, 0.34179688]]" \
|
| 287 |
+
--output_image results/ip_layout.png
|
| 288 |
+
```
|
| 289 |
+
|
| 290 |
+
### 6. Running with the Dev Model
|
| 291 |
+
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:
|
| 292 |
+
|
| 293 |
+
```bash
|
| 294 |
+
python inference.py \
|
| 295 |
+
--model_path /path/to/HiDream-O1-Image-Dev \
|
| 296 |
+
--prompt "A dog holds a sign that says \"HiDream-O1-Image release.\"" \
|
| 297 |
+
--output_image results/t2i_dev.png \
|
| 298 |
+
--model_type dev
|
| 299 |
+
```
|
| 300 |
+
|
| 301 |
+
### Command Line Arguments
|
| 302 |
+
|
| 303 |
+
- `--model_path`: Path to the complete HuggingFace model directory (undistilled or distilled).
|
| 304 |
+
- `--prompt`: Text prompt for the generation or editing task.
|
| 305 |
+
- `--ref_images`: Paths to one or more reference images (optional; space-separated).
|
| 306 |
+
- `--output_image`: Path to save the generated image (default: `output.png`).
|
| 307 |
+
- `--height` / `--width`: Output image dimensions (default: `2048` × `2048`; values snap to valid resolutions internally).
|
| 308 |
+
- `--model_type`: `full` or `dev` (default: `full`). Selects the inference recipe:
|
| 309 |
+
- `full`: 50 steps, guidance scale `5.0`, shift `3.0`, default scheduler.
|
| 310 |
+
- `dev`: 28 steps, guidance scale `0.0`, shift `1.0`, flash scheduler with predefined timesteps.
|
| 311 |
+
- `--seed`: Random seed (default: `32`).
|
| 312 |
+
- `--guidance_scale`: Guidance scale (default: `5.0`). Only effective when `--model_type` is `full`.
|
| 313 |
+
- `--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:262` and `models/pipeline.py:273`. Defaults: `7.5`, `7.5`.
|
| 314 |
+
- `--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:348-350`. Default: `2.5`.
|
| 315 |
+
- `--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`.
|
| 316 |
+
|
| 317 |
+
## Web Demo
|
| 318 |
+
|
| 319 |
+
`app.py` is a self-contained Flask web application that exposes all generation modes. It also integrates the Reasoning-Driven Prompt Agent.
|
| 320 |
+
|
| 321 |
+
### Starting the server
|
| 322 |
+
|
| 323 |
+
```bash
|
| 324 |
+
python app.py \
|
| 325 |
+
--model_path /path/to/HiDream-O1-Image \
|
| 326 |
+
--host 0.0.0.0 \
|
| 327 |
+
--port 7860
|
| 328 |
+
```
|
| 329 |
+
|
| 330 |
+
Then open `http://localhost:7860` in your browser.
|
| 331 |
+
|
| 332 |
+
### Command-line arguments
|
| 333 |
+
|
| 334 |
+
| Argument | Default | Description |
|
| 335 |
+
| :--- | :--- | :--- |
|
| 336 |
+
| `--model_path` | `$HIDREAM_MODEL_PATH` | Path to the checkpoint directory (`HiDream-O1-Image` or `HiDream-O1-Image-Dev`). |
|
| 337 |
+
| `--model_type` | `full` | `full` (50-step) or `dev` (28-step). |
|
| 338 |
+
| `--host` | `0.0.0.0` | Bind address for the Flask server. |
|
| 339 |
+
| `--port` | `7860` | Port for the Flask server. |
|
| 340 |
+
|
| 341 |
+
All four arguments can also be set via environment variables (see `.env.example`): `HIDREAM_MODEL_PATH`, `HIDREAM_MODEL_TYPE`, `HIDREAM_HOST`, and `HIDREAM_PORT`.
|
| 342 |
+
|
| 343 |
+
### Prompt Agent in the UI
|
| 344 |
+
|
| 345 |
+
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).
|
| 346 |
+
|
| 347 |
+
## License
|
| 348 |
+
The code in this repository and the HiDream-O1-Image models are licensed under MIT License.
|
assets/IP.webp
ADDED
|
Git LFS Details
|
assets/IP_2.jpg
ADDED
|
Git LFS Details
|
assets/general.webp
ADDED
|
Git LFS Details
|
assets/leaderboard.png
ADDED
|
Git LFS Details
|
assets/text-layout.webp
ADDED
|
Git LFS Details
|
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 |
+
}
|
language_model/language_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:328ab108a382c237d4cb471d0e3c61f9029de4166618c63a17eed7cac391263d
|
| 3 |
+
size 15136860488
|
lm_head/lm_head.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45994934a736dfe4de2e97589c589aaeea0febe51c1a7b442401e362fb077843
|
| 3 |
+
size 1244659800
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,583 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8804887792,
|
| 4 |
+
"total_size": 0
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm.head": "lm_head/lm_head.safetensors",
|
| 8 |
+
"model.language.model.embed.tokens": "language_model/language_model.safetensors",
|
| 9 |
+
"model.language.model.layers.0.input.layernorm": "language_model/language_model.safetensors",
|
| 10 |
+
"model.language.model.layers.0.mlp.down.proj": "language_model/language_model.safetensors",
|
| 11 |
+
"model.language.model.layers.0.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 12 |
+
"model.language.model.layers.0.mlp.up.proj": "language_model/language_model.safetensors",
|
| 13 |
+
"model.language.model.layers.0.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 14 |
+
"model.language.model.layers.0.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 15 |
+
"model.language.model.layers.0.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 16 |
+
"model.language.model.layers.0.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 17 |
+
"model.language.model.layers.0.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 18 |
+
"model.language.model.layers.0.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 19 |
+
"model.language.model.layers.0.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 20 |
+
"model.language.model.layers.10.input.layernorm": "language_model/language_model.safetensors",
|
| 21 |
+
"model.language.model.layers.10.mlp.down.proj": "language_model/language_model.safetensors",
|
| 22 |
+
"model.language.model.layers.10.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 23 |
+
"model.language.model.layers.10.mlp.up.proj": "language_model/language_model.safetensors",
|
| 24 |
+
"model.language.model.layers.10.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 25 |
+
"model.language.model.layers.10.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 26 |
+
"model.language.model.layers.10.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 27 |
+
"model.language.model.layers.10.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 28 |
+
"model.language.model.layers.10.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 29 |
+
"model.language.model.layers.10.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 30 |
+
"model.language.model.layers.10.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 31 |
+
"model.language.model.layers.11.input.layernorm": "language_model/language_model.safetensors",
|
| 32 |
+
"model.language.model.layers.11.mlp.down.proj": "language_model/language_model.safetensors",
|
| 33 |
+
"model.language.model.layers.11.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 34 |
+
"model.language.model.layers.11.mlp.up.proj": "language_model/language_model.safetensors",
|
| 35 |
+
"model.language.model.layers.11.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 36 |
+
"model.language.model.layers.11.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 37 |
+
"model.language.model.layers.11.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 38 |
+
"model.language.model.layers.11.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 39 |
+
"model.language.model.layers.11.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 40 |
+
"model.language.model.layers.11.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 41 |
+
"model.language.model.layers.11.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 42 |
+
"model.language.model.layers.12.input.layernorm": "language_model/language_model.safetensors",
|
| 43 |
+
"model.language.model.layers.12.mlp.down.proj": "language_model/language_model.safetensors",
|
| 44 |
+
"model.language.model.layers.12.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 45 |
+
"model.language.model.layers.12.mlp.up.proj": "language_model/language_model.safetensors",
|
| 46 |
+
"model.language.model.layers.12.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 47 |
+
"model.language.model.layers.12.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 48 |
+
"model.language.model.layers.12.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 49 |
+
"model.language.model.layers.12.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 50 |
+
"model.language.model.layers.12.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 51 |
+
"model.language.model.layers.12.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 52 |
+
"model.language.model.layers.12.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 53 |
+
"model.language.model.layers.13.input.layernorm": "language_model/language_model.safetensors",
|
| 54 |
+
"model.language.model.layers.13.mlp.down.proj": "language_model/language_model.safetensors",
|
| 55 |
+
"model.language.model.layers.13.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 56 |
+
"model.language.model.layers.13.mlp.up.proj": "language_model/language_model.safetensors",
|
| 57 |
+
"model.language.model.layers.13.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 58 |
+
"model.language.model.layers.13.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 59 |
+
"model.language.model.layers.13.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 60 |
+
"model.language.model.layers.13.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 61 |
+
"model.language.model.layers.13.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 62 |
+
"model.language.model.layers.13.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 63 |
+
"model.language.model.layers.13.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 64 |
+
"model.language.model.layers.14.input.layernorm": "language_model/language_model.safetensors",
|
| 65 |
+
"model.language.model.layers.14.mlp.down.proj": "language_model/language_model.safetensors",
|
| 66 |
+
"model.language.model.layers.14.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 67 |
+
"model.language.model.layers.14.mlp.up.proj": "language_model/language_model.safetensors",
|
| 68 |
+
"model.language.model.layers.14.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 69 |
+
"model.language.model.layers.14.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 70 |
+
"model.language.model.layers.14.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 71 |
+
"model.language.model.layers.14.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 72 |
+
"model.language.model.layers.14.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 73 |
+
"model.language.model.layers.14.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 74 |
+
"model.language.model.layers.14.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 75 |
+
"model.language.model.layers.15.input.layernorm": "language_model/language_model.safetensors",
|
| 76 |
+
"model.language.model.layers.15.mlp.down.proj": "language_model/language_model.safetensors",
|
| 77 |
+
"model.language.model.layers.15.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 78 |
+
"model.language.model.layers.15.mlp.up.proj": "language_model/language_model.safetensors",
|
| 79 |
+
"model.language.model.layers.15.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 80 |
+
"model.language.model.layers.15.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 81 |
+
"model.language.model.layers.15.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 82 |
+
"model.language.model.layers.15.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 83 |
+
"model.language.model.layers.15.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 84 |
+
"model.language.model.layers.15.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 85 |
+
"model.language.model.layers.15.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 86 |
+
"model.language.model.layers.16.input.layernorm": "language_model/language_model.safetensors",
|
| 87 |
+
"model.language.model.layers.16.mlp.down.proj": "language_model/language_model.safetensors",
|
| 88 |
+
"model.language.model.layers.16.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 89 |
+
"model.language.model.layers.16.mlp.up.proj": "language_model/language_model.safetensors",
|
| 90 |
+
"model.language.model.layers.16.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 91 |
+
"model.language.model.layers.16.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 92 |
+
"model.language.model.layers.16.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 93 |
+
"model.language.model.layers.16.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 94 |
+
"model.language.model.layers.16.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 95 |
+
"model.language.model.layers.16.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 96 |
+
"model.language.model.layers.16.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 97 |
+
"model.language.model.layers.17.input.layernorm": "language_model/language_model.safetensors",
|
| 98 |
+
"model.language.model.layers.17.mlp.down.proj": "language_model/language_model.safetensors",
|
| 99 |
+
"model.language.model.layers.17.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 100 |
+
"model.language.model.layers.17.mlp.up.proj": "language_model/language_model.safetensors",
|
| 101 |
+
"model.language.model.layers.17.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 102 |
+
"model.language.model.layers.17.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 103 |
+
"model.language.model.layers.17.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 104 |
+
"model.language.model.layers.17.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 105 |
+
"model.language.model.layers.17.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 106 |
+
"model.language.model.layers.17.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 107 |
+
"model.language.model.layers.17.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 108 |
+
"model.language.model.layers.18.input.layernorm": "language_model/language_model.safetensors",
|
| 109 |
+
"model.language.model.layers.18.mlp.down.proj": "language_model/language_model.safetensors",
|
| 110 |
+
"model.language.model.layers.18.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 111 |
+
"model.language.model.layers.18.mlp.up.proj": "language_model/language_model.safetensors",
|
| 112 |
+
"model.language.model.layers.18.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 113 |
+
"model.language.model.layers.18.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 114 |
+
"model.language.model.layers.18.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 115 |
+
"model.language.model.layers.18.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 116 |
+
"model.language.model.layers.18.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 117 |
+
"model.language.model.layers.18.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 118 |
+
"model.language.model.layers.18.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 119 |
+
"model.language.model.layers.19.input.layernorm": "language_model/language_model.safetensors",
|
| 120 |
+
"model.language.model.layers.19.mlp.down.proj": "language_model/language_model.safetensors",
|
| 121 |
+
"model.language.model.layers.19.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 122 |
+
"model.language.model.layers.19.mlp.up.proj": "language_model/language_model.safetensors",
|
| 123 |
+
"model.language.model.layers.19.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 124 |
+
"model.language.model.layers.19.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 125 |
+
"model.language.model.layers.19.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 126 |
+
"model.language.model.layers.19.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 127 |
+
"model.language.model.layers.19.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 128 |
+
"model.language.model.layers.19.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 129 |
+
"model.language.model.layers.19.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 130 |
+
"model.language.model.layers.1.input.layernorm": "language_model/language_model.safetensors",
|
| 131 |
+
"model.language.model.layers.1.mlp.down.proj": "language_model/language_model.safetensors",
|
| 132 |
+
"model.language.model.layers.1.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 133 |
+
"model.language.model.layers.1.mlp.up.proj": "language_model/language_model.safetensors",
|
| 134 |
+
"model.language.model.layers.1.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 135 |
+
"model.language.model.layers.1.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 136 |
+
"model.language.model.layers.1.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 137 |
+
"model.language.model.layers.1.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 138 |
+
"model.language.model.layers.1.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 139 |
+
"model.language.model.layers.1.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 140 |
+
"model.language.model.layers.1.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 141 |
+
"model.language.model.layers.20.input.layernorm": "language_model/language_model.safetensors",
|
| 142 |
+
"model.language.model.layers.20.mlp.down.proj": "language_model/language_model.safetensors",
|
| 143 |
+
"model.language.model.layers.20.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 144 |
+
"model.language.model.layers.20.mlp.up.proj": "language_model/language_model.safetensors",
|
| 145 |
+
"model.language.model.layers.20.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 146 |
+
"model.language.model.layers.20.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 147 |
+
"model.language.model.layers.20.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 148 |
+
"model.language.model.layers.20.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 149 |
+
"model.language.model.layers.20.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 150 |
+
"model.language.model.layers.20.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 151 |
+
"model.language.model.layers.20.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 152 |
+
"model.language.model.layers.21.input.layernorm": "language_model/language_model.safetensors",
|
| 153 |
+
"model.language.model.layers.21.mlp.down.proj": "language_model/language_model.safetensors",
|
| 154 |
+
"model.language.model.layers.21.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 155 |
+
"model.language.model.layers.21.mlp.up.proj": "language_model/language_model.safetensors",
|
| 156 |
+
"model.language.model.layers.21.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 157 |
+
"model.language.model.layers.21.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 158 |
+
"model.language.model.layers.21.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 159 |
+
"model.language.model.layers.21.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 160 |
+
"model.language.model.layers.21.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 161 |
+
"model.language.model.layers.21.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 162 |
+
"model.language.model.layers.21.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 163 |
+
"model.language.model.layers.22.input.layernorm": "language_model/language_model.safetensors",
|
| 164 |
+
"model.language.model.layers.22.mlp.down.proj": "language_model/language_model.safetensors",
|
| 165 |
+
"model.language.model.layers.22.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 166 |
+
"model.language.model.layers.22.mlp.up.proj": "language_model/language_model.safetensors",
|
| 167 |
+
"model.language.model.layers.22.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 168 |
+
"model.language.model.layers.22.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 169 |
+
"model.language.model.layers.22.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 170 |
+
"model.language.model.layers.22.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 171 |
+
"model.language.model.layers.22.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 172 |
+
"model.language.model.layers.22.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 173 |
+
"model.language.model.layers.22.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 174 |
+
"model.language.model.layers.23.input.layernorm": "language_model/language_model.safetensors",
|
| 175 |
+
"model.language.model.layers.23.mlp.down.proj": "language_model/language_model.safetensors",
|
| 176 |
+
"model.language.model.layers.23.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 177 |
+
"model.language.model.layers.23.mlp.up.proj": "language_model/language_model.safetensors",
|
| 178 |
+
"model.language.model.layers.23.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 179 |
+
"model.language.model.layers.23.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 180 |
+
"model.language.model.layers.23.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 181 |
+
"model.language.model.layers.23.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 182 |
+
"model.language.model.layers.23.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 183 |
+
"model.language.model.layers.23.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 184 |
+
"model.language.model.layers.23.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 185 |
+
"model.language.model.layers.24.input.layernorm": "language_model/language_model.safetensors",
|
| 186 |
+
"model.language.model.layers.24.mlp.down.proj": "language_model/language_model.safetensors",
|
| 187 |
+
"model.language.model.layers.24.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 188 |
+
"model.language.model.layers.24.mlp.up.proj": "language_model/language_model.safetensors",
|
| 189 |
+
"model.language.model.layers.24.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 190 |
+
"model.language.model.layers.24.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 191 |
+
"model.language.model.layers.24.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 192 |
+
"model.language.model.layers.24.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 193 |
+
"model.language.model.layers.24.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 194 |
+
"model.language.model.layers.24.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 195 |
+
"model.language.model.layers.24.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 196 |
+
"model.language.model.layers.25.input.layernorm": "language_model/language_model.safetensors",
|
| 197 |
+
"model.language.model.layers.25.mlp.down.proj": "language_model/language_model.safetensors",
|
| 198 |
+
"model.language.model.layers.25.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 199 |
+
"model.language.model.layers.25.mlp.up.proj": "language_model/language_model.safetensors",
|
| 200 |
+
"model.language.model.layers.25.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 201 |
+
"model.language.model.layers.25.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 202 |
+
"model.language.model.layers.25.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 203 |
+
"model.language.model.layers.25.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 204 |
+
"model.language.model.layers.25.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 205 |
+
"model.language.model.layers.25.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 206 |
+
"model.language.model.layers.25.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 207 |
+
"model.language.model.layers.26.input.layernorm": "language_model/language_model.safetensors",
|
| 208 |
+
"model.language.model.layers.26.mlp.down.proj": "language_model/language_model.safetensors",
|
| 209 |
+
"model.language.model.layers.26.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 210 |
+
"model.language.model.layers.26.mlp.up.proj": "language_model/language_model.safetensors",
|
| 211 |
+
"model.language.model.layers.26.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 212 |
+
"model.language.model.layers.26.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 213 |
+
"model.language.model.layers.26.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 214 |
+
"model.language.model.layers.26.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 215 |
+
"model.language.model.layers.26.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 216 |
+
"model.language.model.layers.26.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 217 |
+
"model.language.model.layers.26.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 218 |
+
"model.language.model.layers.27.input.layernorm": "language_model/language_model.safetensors",
|
| 219 |
+
"model.language.model.layers.27.mlp.down.proj": "language_model/language_model.safetensors",
|
| 220 |
+
"model.language.model.layers.27.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 221 |
+
"model.language.model.layers.27.mlp.up.proj": "language_model/language_model.safetensors",
|
| 222 |
+
"model.language.model.layers.27.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 223 |
+
"model.language.model.layers.27.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 224 |
+
"model.language.model.layers.27.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 225 |
+
"model.language.model.layers.27.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 226 |
+
"model.language.model.layers.27.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 227 |
+
"model.language.model.layers.27.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 228 |
+
"model.language.model.layers.27.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 229 |
+
"model.language.model.layers.28.input.layernorm": "language_model/language_model.safetensors",
|
| 230 |
+
"model.language.model.layers.28.mlp.down.proj": "language_model/language_model.safetensors",
|
| 231 |
+
"model.language.model.layers.28.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 232 |
+
"model.language.model.layers.28.mlp.up.proj": "language_model/language_model.safetensors",
|
| 233 |
+
"model.language.model.layers.28.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 234 |
+
"model.language.model.layers.28.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 235 |
+
"model.language.model.layers.28.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 236 |
+
"model.language.model.layers.28.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 237 |
+
"model.language.model.layers.28.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 238 |
+
"model.language.model.layers.28.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 239 |
+
"model.language.model.layers.28.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 240 |
+
"model.language.model.layers.29.input.layernorm": "language_model/language_model.safetensors",
|
| 241 |
+
"model.language.model.layers.29.mlp.down.proj": "language_model/language_model.safetensors",
|
| 242 |
+
"model.language.model.layers.29.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 243 |
+
"model.language.model.layers.29.mlp.up.proj": "language_model/language_model.safetensors",
|
| 244 |
+
"model.language.model.layers.29.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 245 |
+
"model.language.model.layers.29.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 246 |
+
"model.language.model.layers.29.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 247 |
+
"model.language.model.layers.29.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 248 |
+
"model.language.model.layers.29.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 249 |
+
"model.language.model.layers.29.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 250 |
+
"model.language.model.layers.29.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 251 |
+
"model.language.model.layers.2.input.layernorm": "language_model/language_model.safetensors",
|
| 252 |
+
"model.language.model.layers.2.mlp.down.proj": "language_model/language_model.safetensors",
|
| 253 |
+
"model.language.model.layers.2.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 254 |
+
"model.language.model.layers.2.mlp.up.proj": "language_model/language_model.safetensors",
|
| 255 |
+
"model.language.model.layers.2.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 256 |
+
"model.language.model.layers.2.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 257 |
+
"model.language.model.layers.2.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 258 |
+
"model.language.model.layers.2.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 259 |
+
"model.language.model.layers.2.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 260 |
+
"model.language.model.layers.2.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 261 |
+
"model.language.model.layers.2.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 262 |
+
"model.language.model.layers.30.input.layernorm": "language_model/language_model.safetensors",
|
| 263 |
+
"model.language.model.layers.30.mlp.down.proj": "language_model/language_model.safetensors",
|
| 264 |
+
"model.language.model.layers.30.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 265 |
+
"model.language.model.layers.30.mlp.up.proj": "language_model/language_model.safetensors",
|
| 266 |
+
"model.language.model.layers.30.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 267 |
+
"model.language.model.layers.30.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 268 |
+
"model.language.model.layers.30.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 269 |
+
"model.language.model.layers.30.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 270 |
+
"model.language.model.layers.30.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 271 |
+
"model.language.model.layers.30.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 272 |
+
"model.language.model.layers.30.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 273 |
+
"model.language.model.layers.31.input.layernorm": "language_model/language_model.safetensors",
|
| 274 |
+
"model.language.model.layers.31.mlp.down.proj": "language_model/language_model.safetensors",
|
| 275 |
+
"model.language.model.layers.31.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 276 |
+
"model.language.model.layers.31.mlp.up.proj": "language_model/language_model.safetensors",
|
| 277 |
+
"model.language.model.layers.31.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 278 |
+
"model.language.model.layers.31.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 279 |
+
"model.language.model.layers.31.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 280 |
+
"model.language.model.layers.31.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 281 |
+
"model.language.model.layers.31.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 282 |
+
"model.language.model.layers.31.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 283 |
+
"model.language.model.layers.31.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 284 |
+
"model.language.model.layers.32.input.layernorm": "language_model/language_model.safetensors",
|
| 285 |
+
"model.language.model.layers.32.mlp.down.proj": "language_model/language_model.safetensors",
|
| 286 |
+
"model.language.model.layers.32.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 287 |
+
"model.language.model.layers.32.mlp.up.proj": "language_model/language_model.safetensors",
|
| 288 |
+
"model.language.model.layers.32.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 289 |
+
"model.language.model.layers.32.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 290 |
+
"model.language.model.layers.32.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 291 |
+
"model.language.model.layers.32.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 292 |
+
"model.language.model.layers.32.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 293 |
+
"model.language.model.layers.32.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 294 |
+
"model.language.model.layers.32.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 295 |
+
"model.language.model.layers.33.input.layernorm": "language_model/language_model.safetensors",
|
| 296 |
+
"model.language.model.layers.33.mlp.down.proj": "language_model/language_model.safetensors",
|
| 297 |
+
"model.language.model.layers.33.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 298 |
+
"model.language.model.layers.33.mlp.up.proj": "language_model/language_model.safetensors",
|
| 299 |
+
"model.language.model.layers.33.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 300 |
+
"model.language.model.layers.33.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 301 |
+
"model.language.model.layers.33.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 302 |
+
"model.language.model.layers.33.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 303 |
+
"model.language.model.layers.33.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 304 |
+
"model.language.model.layers.33.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 305 |
+
"model.language.model.layers.33.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 306 |
+
"model.language.model.layers.34.input.layernorm": "language_model/language_model.safetensors",
|
| 307 |
+
"model.language.model.layers.34.mlp.down.proj": "language_model/language_model.safetensors",
|
| 308 |
+
"model.language.model.layers.34.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 309 |
+
"model.language.model.layers.34.mlp.up.proj": "language_model/language_model.safetensors",
|
| 310 |
+
"model.language.model.layers.34.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 311 |
+
"model.language.model.layers.34.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 312 |
+
"model.language.model.layers.34.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 313 |
+
"model.language.model.layers.34.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 314 |
+
"model.language.model.layers.34.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 315 |
+
"model.language.model.layers.34.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 316 |
+
"model.language.model.layers.34.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 317 |
+
"model.language.model.layers.35.input.layernorm": "language_model/language_model.safetensors",
|
| 318 |
+
"model.language.model.layers.35.mlp.down.proj": "language_model/language_model.safetensors",
|
| 319 |
+
"model.language.model.layers.35.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 320 |
+
"model.language.model.layers.35.mlp.up.proj": "language_model/language_model.safetensors",
|
| 321 |
+
"model.language.model.layers.35.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 322 |
+
"model.language.model.layers.35.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 323 |
+
"model.language.model.layers.35.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 324 |
+
"model.language.model.layers.35.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 325 |
+
"model.language.model.layers.35.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 326 |
+
"model.language.model.layers.35.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 327 |
+
"model.language.model.layers.35.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 328 |
+
"model.language.model.layers.3.input.layernorm": "language_model/language_model.safetensors",
|
| 329 |
+
"model.language.model.layers.3.mlp.down.proj": "language_model/language_model.safetensors",
|
| 330 |
+
"model.language.model.layers.3.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 331 |
+
"model.language.model.layers.3.mlp.up.proj": "language_model/language_model.safetensors",
|
| 332 |
+
"model.language.model.layers.3.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 333 |
+
"model.language.model.layers.3.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 334 |
+
"model.language.model.layers.3.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 335 |
+
"model.language.model.layers.3.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 336 |
+
"model.language.model.layers.3.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 337 |
+
"model.language.model.layers.3.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 338 |
+
"model.language.model.layers.3.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 339 |
+
"model.language.model.layers.4.input.layernorm": "language_model/language_model.safetensors",
|
| 340 |
+
"model.language.model.layers.4.mlp.down.proj": "language_model/language_model.safetensors",
|
| 341 |
+
"model.language.model.layers.4.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 342 |
+
"model.language.model.layers.4.mlp.up.proj": "language_model/language_model.safetensors",
|
| 343 |
+
"model.language.model.layers.4.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 344 |
+
"model.language.model.layers.4.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 345 |
+
"model.language.model.layers.4.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 346 |
+
"model.language.model.layers.4.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 347 |
+
"model.language.model.layers.4.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 348 |
+
"model.language.model.layers.4.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 349 |
+
"model.language.model.layers.4.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 350 |
+
"model.language.model.layers.5.input.layernorm": "language_model/language_model.safetensors",
|
| 351 |
+
"model.language.model.layers.5.mlp.down.proj": "language_model/language_model.safetensors",
|
| 352 |
+
"model.language.model.layers.5.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 353 |
+
"model.language.model.layers.5.mlp.up.proj": "language_model/language_model.safetensors",
|
| 354 |
+
"model.language.model.layers.5.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 355 |
+
"model.language.model.layers.5.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 356 |
+
"model.language.model.layers.5.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 357 |
+
"model.language.model.layers.5.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 358 |
+
"model.language.model.layers.5.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 359 |
+
"model.language.model.layers.5.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 360 |
+
"model.language.model.layers.5.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 361 |
+
"model.language.model.layers.6.input.layernorm": "language_model/language_model.safetensors",
|
| 362 |
+
"model.language.model.layers.6.mlp.down.proj": "language_model/language_model.safetensors",
|
| 363 |
+
"model.language.model.layers.6.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 364 |
+
"model.language.model.layers.6.mlp.up.proj": "language_model/language_model.safetensors",
|
| 365 |
+
"model.language.model.layers.6.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 366 |
+
"model.language.model.layers.6.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 367 |
+
"model.language.model.layers.6.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 368 |
+
"model.language.model.layers.6.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 369 |
+
"model.language.model.layers.6.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 370 |
+
"model.language.model.layers.6.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 371 |
+
"model.language.model.layers.6.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 372 |
+
"model.language.model.layers.7.input.layernorm": "language_model/language_model.safetensors",
|
| 373 |
+
"model.language.model.layers.7.mlp.down.proj": "language_model/language_model.safetensors",
|
| 374 |
+
"model.language.model.layers.7.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 375 |
+
"model.language.model.layers.7.mlp.up.proj": "language_model/language_model.safetensors",
|
| 376 |
+
"model.language.model.layers.7.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 377 |
+
"model.language.model.layers.7.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 378 |
+
"model.language.model.layers.7.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 379 |
+
"model.language.model.layers.7.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 380 |
+
"model.language.model.layers.7.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 381 |
+
"model.language.model.layers.7.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 382 |
+
"model.language.model.layers.7.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 383 |
+
"model.language.model.layers.8.input.layernorm": "language_model/language_model.safetensors",
|
| 384 |
+
"model.language.model.layers.8.mlp.down.proj": "language_model/language_model.safetensors",
|
| 385 |
+
"model.language.model.layers.8.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 386 |
+
"model.language.model.layers.8.mlp.up.proj": "language_model/language_model.safetensors",
|
| 387 |
+
"model.language.model.layers.8.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 388 |
+
"model.language.model.layers.8.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 389 |
+
"model.language.model.layers.8.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 390 |
+
"model.language.model.layers.8.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 391 |
+
"model.language.model.layers.8.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 392 |
+
"model.language.model.layers.8.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 393 |
+
"model.language.model.layers.8.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 394 |
+
"model.language.model.layers.9.input.layernorm": "language_model/language_model.safetensors",
|
| 395 |
+
"model.language.model.layers.9.mlp.down.proj": "language_model/language_model.safetensors",
|
| 396 |
+
"model.language.model.layers.9.mlp.gate.proj": "language_model/language_model.safetensors",
|
| 397 |
+
"model.language.model.layers.9.mlp.up.proj": "language_model/language_model.safetensors",
|
| 398 |
+
"model.language.model.layers.9.post.attention.layernorm": "language_model/language_model.safetensors",
|
| 399 |
+
"model.language.model.layers.9.self.attn.k.norm": "language_model/language_model.safetensors",
|
| 400 |
+
"model.language.model.layers.9.self.attn.k.proj": "language_model/language_model.safetensors",
|
| 401 |
+
"model.language.model.layers.9.self.attn.o.proj": "language_model/language_model.safetensors",
|
| 402 |
+
"model.language.model.layers.9.self.attn.q.norm": "language_model/language_model.safetensors",
|
| 403 |
+
"model.language.model.layers.9.self.attn.q.proj": "language_model/language_model.safetensors",
|
| 404 |
+
"model.language.model.layers.9.self.attn.v.proj": "language_model/language_model.safetensors",
|
| 405 |
+
"model.language.model.norm": "language_model/language_model.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 408 |
+
"model.visual.blocks.0.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 410 |
+
"model.visual.blocks.0.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 411 |
+
"model.visual.blocks.0.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 412 |
+
"model.visual.blocks.10.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 413 |
+
"model.visual.blocks.10.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 414 |
+
"model.visual.blocks.10.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 415 |
+
"model.visual.blocks.10.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 416 |
+
"model.visual.blocks.10.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 417 |
+
"model.visual.blocks.10.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 418 |
+
"model.visual.blocks.11.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 419 |
+
"model.visual.blocks.11.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 420 |
+
"model.visual.blocks.11.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 421 |
+
"model.visual.blocks.11.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 422 |
+
"model.visual.blocks.11.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 423 |
+
"model.visual.blocks.11.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 424 |
+
"model.visual.blocks.12.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 425 |
+
"model.visual.blocks.12.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 426 |
+
"model.visual.blocks.12.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 427 |
+
"model.visual.blocks.12.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 428 |
+
"model.visual.blocks.12.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 429 |
+
"model.visual.blocks.12.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 430 |
+
"model.visual.blocks.13.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 431 |
+
"model.visual.blocks.13.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 432 |
+
"model.visual.blocks.13.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 433 |
+
"model.visual.blocks.13.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 434 |
+
"model.visual.blocks.13.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 435 |
+
"model.visual.blocks.13.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 436 |
+
"model.visual.blocks.14.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 437 |
+
"model.visual.blocks.14.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 438 |
+
"model.visual.blocks.14.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 439 |
+
"model.visual.blocks.14.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 440 |
+
"model.visual.blocks.14.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 441 |
+
"model.visual.blocks.14.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 442 |
+
"model.visual.blocks.15.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 443 |
+
"model.visual.blocks.15.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 444 |
+
"model.visual.blocks.15.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 445 |
+
"model.visual.blocks.15.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 446 |
+
"model.visual.blocks.15.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 447 |
+
"model.visual.blocks.15.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 448 |
+
"model.visual.blocks.16.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 449 |
+
"model.visual.blocks.16.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 450 |
+
"model.visual.blocks.16.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 451 |
+
"model.visual.blocks.16.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 452 |
+
"model.visual.blocks.16.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 453 |
+
"model.visual.blocks.16.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 454 |
+
"model.visual.blocks.17.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 455 |
+
"model.visual.blocks.17.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 456 |
+
"model.visual.blocks.17.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 457 |
+
"model.visual.blocks.17.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 458 |
+
"model.visual.blocks.17.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 459 |
+
"model.visual.blocks.17.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 460 |
+
"model.visual.blocks.18.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 461 |
+
"model.visual.blocks.18.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 462 |
+
"model.visual.blocks.18.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 463 |
+
"model.visual.blocks.18.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 464 |
+
"model.visual.blocks.18.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 465 |
+
"model.visual.blocks.18.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 466 |
+
"model.visual.blocks.19.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 467 |
+
"model.visual.blocks.19.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 468 |
+
"model.visual.blocks.19.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 469 |
+
"model.visual.blocks.19.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 470 |
+
"model.visual.blocks.19.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 471 |
+
"model.visual.blocks.19.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 472 |
+
"model.visual.blocks.1.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 473 |
+
"model.visual.blocks.1.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 474 |
+
"model.visual.blocks.1.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 475 |
+
"model.visual.blocks.1.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 476 |
+
"model.visual.blocks.1.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 477 |
+
"model.visual.blocks.1.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 478 |
+
"model.visual.blocks.20.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 479 |
+
"model.visual.blocks.20.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 480 |
+
"model.visual.blocks.20.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 481 |
+
"model.visual.blocks.20.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 482 |
+
"model.visual.blocks.20.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 483 |
+
"model.visual.blocks.20.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 484 |
+
"model.visual.blocks.21.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 485 |
+
"model.visual.blocks.21.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 486 |
+
"model.visual.blocks.21.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 487 |
+
"model.visual.blocks.21.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 488 |
+
"model.visual.blocks.21.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 489 |
+
"model.visual.blocks.21.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 490 |
+
"model.visual.blocks.22.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 491 |
+
"model.visual.blocks.22.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 492 |
+
"model.visual.blocks.22.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 493 |
+
"model.visual.blocks.22.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 494 |
+
"model.visual.blocks.22.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 495 |
+
"model.visual.blocks.22.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 496 |
+
"model.visual.blocks.23.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 497 |
+
"model.visual.blocks.23.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 498 |
+
"model.visual.blocks.23.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 499 |
+
"model.visual.blocks.23.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 500 |
+
"model.visual.blocks.23.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 501 |
+
"model.visual.blocks.23.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 502 |
+
"model.visual.blocks.24.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 503 |
+
"model.visual.blocks.24.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 504 |
+
"model.visual.blocks.24.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 505 |
+
"model.visual.blocks.24.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 506 |
+
"model.visual.blocks.24.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 507 |
+
"model.visual.blocks.24.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 508 |
+
"model.visual.blocks.25.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 509 |
+
"model.visual.blocks.25.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 510 |
+
"model.visual.blocks.25.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 511 |
+
"model.visual.blocks.25.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 512 |
+
"model.visual.blocks.25.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 513 |
+
"model.visual.blocks.25.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 514 |
+
"model.visual.blocks.26.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 515 |
+
"model.visual.blocks.26.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 516 |
+
"model.visual.blocks.26.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 517 |
+
"model.visual.blocks.26.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 518 |
+
"model.visual.blocks.26.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 519 |
+
"model.visual.blocks.26.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 520 |
+
"model.visual.blocks.2.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 521 |
+
"model.visual.blocks.2.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 522 |
+
"model.visual.blocks.2.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 523 |
+
"model.visual.blocks.2.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 524 |
+
"model.visual.blocks.2.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 525 |
+
"model.visual.blocks.2.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 526 |
+
"model.visual.blocks.3.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 527 |
+
"model.visual.blocks.3.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 528 |
+
"model.visual.blocks.3.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 529 |
+
"model.visual.blocks.3.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 530 |
+
"model.visual.blocks.3.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 531 |
+
"model.visual.blocks.3.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 532 |
+
"model.visual.blocks.4.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 533 |
+
"model.visual.blocks.4.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 534 |
+
"model.visual.blocks.4.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 535 |
+
"model.visual.blocks.4.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 536 |
+
"model.visual.blocks.4.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 537 |
+
"model.visual.blocks.4.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 538 |
+
"model.visual.blocks.5.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 539 |
+
"model.visual.blocks.5.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 540 |
+
"model.visual.blocks.5.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 541 |
+
"model.visual.blocks.5.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 542 |
+
"model.visual.blocks.5.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 543 |
+
"model.visual.blocks.5.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 544 |
+
"model.visual.blocks.6.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 545 |
+
"model.visual.blocks.6.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 546 |
+
"model.visual.blocks.6.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 547 |
+
"model.visual.blocks.6.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 548 |
+
"model.visual.blocks.6.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 549 |
+
"model.visual.blocks.6.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 550 |
+
"model.visual.blocks.7.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 551 |
+
"model.visual.blocks.7.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 552 |
+
"model.visual.blocks.7.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 553 |
+
"model.visual.blocks.7.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 554 |
+
"model.visual.blocks.7.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 555 |
+
"model.visual.blocks.7.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 556 |
+
"model.visual.blocks.8.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 557 |
+
"model.visual.blocks.8.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 558 |
+
"model.visual.blocks.8.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 559 |
+
"model.visual.blocks.8.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 560 |
+
"model.visual.blocks.8.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 561 |
+
"model.visual.blocks.8.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 562 |
+
"model.visual.blocks.9.attn.proj": "visual_encoder/visual_encoder.safetensors",
|
| 563 |
+
"model.visual.blocks.9.attn.qkv": "visual_encoder/visual_encoder.safetensors",
|
| 564 |
+
"model.visual.blocks.9.mlp.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 565 |
+
"model.visual.blocks.9.mlp.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 566 |
+
"model.visual.blocks.9.norm1": "visual_encoder/visual_encoder.safetensors",
|
| 567 |
+
"model.visual.blocks.9.norm2": "visual_encoder/visual_encoder.safetensors",
|
| 568 |
+
"model.visual.deepstack.merger.list.0.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 569 |
+
"model.visual.deepstack.merger.list.0.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 570 |
+
"model.visual.deepstack.merger.list.0.norm": "visual_encoder/visual_encoder.safetensors",
|
| 571 |
+
"model.visual.deepstack.merger.list.1.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 572 |
+
"model.visual.deepstack.merger.list.1.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 573 |
+
"model.visual.deepstack.merger.list.1.norm": "visual_encoder/visual_encoder.safetensors",
|
| 574 |
+
"model.visual.deepstack.merger.list.2.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 575 |
+
"model.visual.deepstack.merger.list.2.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 576 |
+
"model.visual.deepstack.merger.list.2.norm": "visual_encoder/visual_encoder.safetensors",
|
| 577 |
+
"model.visual.merger.linear.fc1": "visual_encoder/visual_encoder.safetensors",
|
| 578 |
+
"model.visual.merger.linear.fc2": "visual_encoder/visual_encoder.safetensors",
|
| 579 |
+
"model.visual.merger.norm": "visual_encoder/visual_encoder.safetensors",
|
| 580 |
+
"model.visual.patch.embed.proj": "visual_encoder/visual_encoder.safetensors",
|
| 581 |
+
"model.visual.pos.embed": "visual_encoder/visual_encoder.safetensors"
|
| 582 |
+
}
|
| 583 |
+
}
|
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 |
+
}
|
visual_encoder/visual_encoder.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2afbb89087941d90578b2ae1731969ed67860e9661951bbfdc6fbc62cfcb21a
|
| 3 |
+
size 6095448
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|