Upload Macro-OmniGen2 model
Browse files- .gitattributes +9 -0
- README.md +228 -0
- assets/brand.png +3 -0
- assets/efficiency.png +3 -0
- assets/examples_edit.png +3 -0
- assets/examples_subject.png +3 -0
- assets/teaser.jpg +3 -0
- assets/teaser.png +3 -0
- mllm/config.json +65 -0
- mllm/generation_config.json +15 -0
- mllm/model-00001-of-00004.safetensors +3 -0
- mllm/model-00002-of-00004.safetensors +3 -0
- mllm/model-00003-of-00004.safetensors +3 -0
- mllm/model-00004-of-00004.safetensors +3 -0
- mllm/model.safetensors.index.json +831 -0
- mllm_processor/added_tokens.json +28 -0
- mllm_processor/chat_template.json +3 -0
- mllm_processor/merges.txt +0 -0
- mllm_processor/preprocessor_config.json +29 -0
- mllm_processor/special_tokens_map.json +31 -0
- mllm_processor/tokenizer.json +3 -0
- mllm_processor/tokenizer_config.json +241 -0
- mllm_processor/vocab.json +0 -0
- model_index.json +24 -0
- processor/added_tokens.json +28 -0
- processor/chat_template.json +3 -0
- processor/merges.txt +0 -0
- processor/preprocessor_config.json +29 -0
- processor/special_tokens_map.json +31 -0
- processor/tokenizer.json +3 -0
- processor/tokenizer_config.json +241 -0
- processor/vocab.json +0 -0
- scheduler/__pycache__/scheduling_flow_match_euler_discrete.cpython-310.pyc +0 -0
- scheduler/__pycache__/scheduling_flow_match_euler_discrete.cpython-311.pyc +0 -0
- scheduler/__pycache__/scheduling_flow_match_euler_discrete.cpython-312.pyc +0 -0
- scheduler/scheduler_config.json +6 -0
- scheduler/scheduling_flow_match_euler_discrete.py +229 -0
- time_caption_context_reinit/config.json +27 -0
- time_caption_context_reinit/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- time_caption_context_reinit/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- time_caption_context_reinit/diffusion_pytorch_model.safetensors.index.json +589 -0
- time_caption_reinit/config.json +27 -0
- time_caption_reinit/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- time_caption_reinit/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- time_caption_reinit/diffusion_pytorch_model.safetensors.index.json +589 -0
- transformer/config.json +28 -0
- transformer/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +38 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,12 @@ 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 |
+
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
mllm_processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
assets/brand.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
assets/examples_edit.png filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
assets/examples_subject.png filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
assets/teaser.png filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
assets/efficiency.png filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
assets/teaser.jpg filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: any-to-any
|
| 4 |
+
library_name: diffusers
|
| 5 |
+
---
|
| 6 |
+
<p align="center">
|
| 7 |
+
<a href="https://github.com/Ve<p align="center">
|
| 8 |
+
<img src="assets/brand.png" width="65%">
|
| 9 |
+
</p>
|
| 10 |
+
|
| 11 |
+
<p align="center">
|
| 12 |
+
<a href="https://vectorspacelab.github.io/OmniGen2"><img src="https://img.shields.io/badge/Project%20Page-OmniGen2-yellow" alt="project page"></a>
|
| 13 |
+
<a href="https://arxiv.org/abs/2506.18871"><img src="https://img.shields.io/badge/arXiv%20paper-2506.18871-b31b1b.svg" alt="arxiv"></a>
|
| 14 |
+
<a href="https://github.com/VectorSpaceLab/OmniGen2?tab=readme-ov-file#-gradio-demo"><img src="https://img.shields.io/badge/Online%20Demo-🤗-blue" alt="demo"></a>
|
| 15 |
+
<a href="https://huggingface.co/spaces/OmniGen2/OmniGen2"><img src="https://img.shields.io/badge/HF%20Spaces-🤗-lightblue" alt="demo"></a>
|
| 16 |
+
<a href="https://huggingface.co/OmniGen2/OmniGen2"><img src="https://img.shields.io/badge/Model-🤗-yellow" alt="model"></a>
|
| 17 |
+
<a href="https://huggingface.co/datasets/OmniGen2/OmniContext"><img src="https://img.shields.io/badge/Benchmark-🤗-yellow" alt="model"></a>
|
| 18 |
+
<a href="https://huggingface.co/datasets/OmniGen2/X2I2"><img src="https://img.shields.io/badge/Dataset-🤗-yellow" alt="model"></a>
|
| 19 |
+
</p>
|
| 20 |
+
|
| 21 |
+
<h4 align="center">
|
| 22 |
+
<p>
|
| 23 |
+
<a href=#-news>News</a> |
|
| 24 |
+
<a href=#-quick-start>Quick Start</a> |
|
| 25 |
+
<a href=#-usage-tips>Usage Tips</a> |
|
| 26 |
+
<a href=#-gradio-demo>Online Demos</a> |
|
| 27 |
+
<a href="#heart-citing-us">Citation</a> |
|
| 28 |
+
<a href="#license">License</a>
|
| 29 |
+
<p>
|
| 30 |
+
</h4>
|
| 31 |
+
|
| 32 |
+
## 🔥 News
|
| 33 |
+
- **2025-07-05**: Training datasets [X2I2](https://huggingface.co/datasets/OmniGen2/X2I2) are available.
|
| 34 |
+
- **2025-07-03**: OmniGen2 now supports [TeaCache](https://github.com/ali-vilab/TeaCache) and [TaylorSeer](https://github.com/Shenyi-Z/TaylorSeer) for faster inference, see [Usage Tips](#-usage-tips) for details. Thanks @legitnull for great [TeaCache-PR](https://github.com/VectorSpaceLab/OmniGen2/pull/52) and [TaylorSeer-PR](https://github.com/VectorSpaceLab/OmniGen2/pull/76).
|
| 35 |
+
- **2025-07-01**: OmniGen2 is supported by [ComfyUI official](https://comfyanonymous.github.io/ComfyUI_examples/omnigen), thanks !!
|
| 36 |
+
- **2025-06-30**: Training code is available, see [fine-tuning](docs/FINETUNE.md) for details.
|
| 37 |
+
- **2025-06-28**: We release [OmniContext](https://huggingface.co/datasets/OmniGen2/OmniContext) benchmark. The evaluation codes are in [omnicontext](https://github.com/VectorSpaceLab/OmniGen2/tree/main/omnicontext).
|
| 38 |
+
- **2025-06-24**: [Technical Report](https://arxiv.org/abs/2506.18871) is available.
|
| 39 |
+
- **2025-06-23**: We’ve updated our code and HF model—OmniGen2 now runs *without* `flash-attn`. Users can still install it for optimal performance.
|
| 40 |
+
- **2025-06-20**: Updated [resource requirements](#-resources-requirement), adding CPU offload support for devices with limited VRAM.
|
| 41 |
+
- **2025-06-16**: [Gradio](https://github.com/VectorSpaceLab/OmniGen2?tab=readme-ov-file#-gradio-demo) and [Jupyter](https://github.com/VectorSpaceLab/OmniGen2/blob/main/example.ipynb) is available. Online Gradio Demo: [Demo1](https://9c4426d27c3b9ecbed.gradio.live); [Chat-Demo1](https://0351497834a4d7226c.gradio.live); see more demo links in [gradio section](https://github.com/VectorSpaceLab/OmniGen2?tab=readme-ov-file#-gradio-demo)
|
| 42 |
+
- **2025-06-16**: We release **OmniGen2**, a multimodal generation model, model weights can be accessed in [huggingface](https://huggingface.co/OmniGen2/OmniGen2) and [modelscope](https://www.modelscope.cn/models/OmniGen2/OmniGen2).
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
## Introduction
|
| 46 |
+
**OmniGen2** is a powerful and efficient unified multimodal model. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. OmniGen2 has competitive performance across four primary capabilities:
|
| 47 |
+
|
| 48 |
+
- **Visual Understanding**: Inherits the robust ability to interpret and analyze image content from its Qwen-VL-2.5 foundation.
|
| 49 |
+
- **Text-to-Image Generation**: Creates high-fidelity and aesthetically pleasing images from textual prompts.
|
| 50 |
+
- **Instruction-guided Image Editing**: Executes complex, instruction-based image modifications with high precision, achieving state-of-the-art performance among open-source models.
|
| 51 |
+
- **In-context Generation**: A versatile capability to process and flexibly combine diverse inputs—including humans, reference objects, and scenes—to produce novel and coherent visual outputs.
|
| 52 |
+
|
| 53 |
+
As an open-source project, OmniGen2 provides a powerful yet resource-efficient foundation for researchers and developers exploring the frontiers of controllable and personalized generative AI.
|
| 54 |
+
|
| 55 |
+
**We will release the training code, dataset, and data construction pipeline soon. Stay tuned!**
|
| 56 |
+
|
| 57 |
+
<p align="center">
|
| 58 |
+
<img src="assets/teaser.jpg" width="95%">
|
| 59 |
+
<br>
|
| 60 |
+
<em>Demonstration of OmniGen2's overall capabilities.</em>
|
| 61 |
+
</p>
|
| 62 |
+
|
| 63 |
+
<p align="center">
|
| 64 |
+
<img src="assets/examples_edit.png" width="95%">
|
| 65 |
+
<br>
|
| 66 |
+
<em>Demonstration of OmniGen2's image editing capabilities.</em>
|
| 67 |
+
</p>
|
| 68 |
+
|
| 69 |
+
<p align="center">
|
| 70 |
+
<img src="assets/examples_subject.png" width="95%">
|
| 71 |
+
<br>
|
| 72 |
+
<em>Demonstration of OmniGen2's in-context generation capabilities.</em>
|
| 73 |
+
</p>
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
## 📌 TODO
|
| 78 |
+
- [x] Technical report.
|
| 79 |
+
- [x] Support CPU offload and improve inference efficiency.
|
| 80 |
+
- [x] In-context generation benchmark: **OmniContext**.
|
| 81 |
+
- [ ] Integration of diffusers.
|
| 82 |
+
- [x] Training datasets.
|
| 83 |
+
- [ ] Training data construction pipeline.
|
| 84 |
+
- [ ] ComfyUI Demo (**commuity support will be greatly appreciated!**).
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
## 🚀 Quick Start
|
| 88 |
+
|
| 89 |
+
### 🛠️ Environment Setup
|
| 90 |
+
|
| 91 |
+
#### ✅ Recommended Setup
|
| 92 |
+
|
| 93 |
+
```bash
|
| 94 |
+
# 1. Clone the repo
|
| 95 |
+
git clone git@github.com:VectorSpaceLab/OmniGen2.git
|
| 96 |
+
cd OmniGen2
|
| 97 |
+
|
| 98 |
+
# 2. (Optional) Create a clean Python environment
|
| 99 |
+
conda create -n omnigen2 python=3.11
|
| 100 |
+
conda activate omnigen2
|
| 101 |
+
|
| 102 |
+
# 3. Install dependencies
|
| 103 |
+
# 3.1 Install PyTorch (choose correct CUDA version)
|
| 104 |
+
pip install torch==2.6.0 torchvision --extra-index-url https://download.pytorch.org/whl/cu124
|
| 105 |
+
|
| 106 |
+
# 3.2 Install other required packages
|
| 107 |
+
pip install -r requirements.txt
|
| 108 |
+
|
| 109 |
+
# Note: Version 2.7.4.post1 is specified for compatibility with CUDA 12.4.
|
| 110 |
+
# Feel free to use a newer version if you use CUDA 12.6 or they fixed this compatibility issue.
|
| 111 |
+
# OmniGen2 runs even without flash-attn, though we recommend install it for best performance.
|
| 112 |
+
pip install flash-attn==2.7.4.post1 --no-build-isolation
|
| 113 |
+
```
|
| 114 |
+
|
| 115 |
+
#### 🌏 For users in Mainland China
|
| 116 |
+
|
| 117 |
+
```bash
|
| 118 |
+
# Install PyTorch from a domestic mirror
|
| 119 |
+
pip install torch==2.6.0 torchvision --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu124
|
| 120 |
+
|
| 121 |
+
# Install other dependencies from Tsinghua mirror
|
| 122 |
+
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
|
| 123 |
+
|
| 124 |
+
# Note: Version 2.7.4.post1 is specified for compatibility with CUDA 12.4.
|
| 125 |
+
# Feel free to use a newer version if you use CUDA 12.6 or they fixed this compatibility issue.
|
| 126 |
+
# OmniGen2 runs even without flash-attn, though we recommend install it for best performance.
|
| 127 |
+
pip install flash-attn==2.7.4.post1 --no-build-isolation -i https://pypi.tuna.tsinghua.edu.cn/simple
|
| 128 |
+
```
|
| 129 |
+
|
| 130 |
+
---
|
| 131 |
+
|
| 132 |
+
### 🧪 Run Examples
|
| 133 |
+
|
| 134 |
+
```bash
|
| 135 |
+
# Visual Understanding
|
| 136 |
+
bash example_understanding.sh
|
| 137 |
+
|
| 138 |
+
# Text-to-image generation
|
| 139 |
+
bash example_t2i.sh
|
| 140 |
+
|
| 141 |
+
# Instruction-guided image editing
|
| 142 |
+
bash example_edit.sh
|
| 143 |
+
|
| 144 |
+
# In-context generation
|
| 145 |
+
bash example_in_context_generation.sh
|
| 146 |
+
```
|
| 147 |
+
|
| 148 |
+
---
|
| 149 |
+
|
| 150 |
+
### 🌐 Gradio Demo
|
| 151 |
+
|
| 152 |
+
* **Online Demo**: [HF Spaces](https://huggingface.co/spaces/OmniGen2/OmniGen2). Beyond Hugging Face Spaces, we are *temporarily* allocating additional GPU resources to ensure smooth access to the online demos. If you notice a long queue for a particular link, please try other links:
|
| 153 |
+
|
| 154 |
+
[Demo1](https://8f10329141d53b6884.gradio.live), [Demo2](https://110863cb06c6c44bd2.gradio.live), [Demo3](https://19b0952eb3cf0d2243.gradio.live), [Demo4](https://981758b17b4197aea7.gradio.live)
|
| 155 |
+
|
| 156 |
+
[Chat-Demo1](https://9315447fc78ef638e3.gradio.live), [Chat-Demo2](https://abe054be89543e4cef.gradio.live), [Chat-Demo3](https://4aa913765db00bbe51.gradio.live), [Chat-Demo4](https://f28a8718565627d2cb.gradio.live)
|
| 157 |
+
|
| 158 |
+
<!-- [Available on Hugging Face Spaces 🚀](https://huggingface.co/spaces/Shitao/OmniGen2) -->
|
| 159 |
+
|
| 160 |
+
* **Run Locally**:
|
| 161 |
+
```bash
|
| 162 |
+
# for only generating image
|
| 163 |
+
pip install gradio
|
| 164 |
+
python app.py
|
| 165 |
+
# Optional: Share demo with public link (You need to be able to access huggingface)
|
| 166 |
+
python app.py --share
|
| 167 |
+
|
| 168 |
+
# for generating image or text
|
| 169 |
+
pip install gradio
|
| 170 |
+
python app_chat.py
|
| 171 |
+
```
|
| 172 |
+
|
| 173 |
+
## 💡 Usage Tips
|
| 174 |
+
To achieve optimal results with OmniGen2, you can adjust the following key hyperparameters based on your specific use case.
|
| 175 |
+
- `text_guidance_scale`: Controls how strictly the output adheres to the text prompt (Classifier-Free Guidance).
|
| 176 |
+
- `image_guidance_scale`: This controls how much the final image should resemble the input reference image.
|
| 177 |
+
- **The Trade-off**: A higher value makes the output more faithful to the reference image's structure and style, but it might ignore parts of your text prompt. A lower value (~1.5) gives the text prompt more influence.
|
| 178 |
+
- **Tip**: For image editing task, we recommend to set it between 1.2 and 2.0; for in-context generateion task, a higher image_guidance_scale will maintian more details in input images, and we recommend to set it between 2.5 and 3.0.
|
| 179 |
+
- `max_pixels`: Automatically resizes images when their total pixel count (width × height) exceeds this limit, while maintaining its aspect ratio. This helps manage performance and memory usage.
|
| 180 |
+
- **Tip**: Default value is 1024*1024. You can reduce this value if you encounter memory issues.
|
| 181 |
+
- `max_input_image_side_length`: Maximum side length for input images.
|
| 182 |
+
- `negative_prompt`: Tell the model what you don't want to see in the image.
|
| 183 |
+
- **Example**: blurry, low quality, text, watermark
|
| 184 |
+
- **Tip**: For the best results, try experimenting with different negative prompts. If you're not sure, just use the default negative prompt.
|
| 185 |
+
- `enable_model_cpu_offload`: **Reduces VRAM usage by nearly 50% with a negligible impact on speed**.
|
| 186 |
+
- This is achieved by offloading the model weights to CPU RAM when they are not in use.
|
| 187 |
+
- See: [Model Offloading](https://huggingface.co/docs/diffusers/optimization/memory#model-offloading)
|
| 188 |
+
- `enable_sequential_cpu_offload`: Minimizes VRAM usage to less than 3GB, but at the cost of significantly slower performance.
|
| 189 |
+
- This works by offloading the model in submodules and loading them onto the GPU sequentially as needed.
|
| 190 |
+
- See: [CPU Offloading](https://huggingface.co/docs/diffusers/optimization/memory#cpu-offloading)
|
| 191 |
+
- `cfg_range_start`, `cfg_range_end`: Define the timestep range where CFG is applied. Per this [paper](https://arxiv.org/abs/2404.07724), reducing `cfg_range_end` can significantly decrease inference time with a negligible impact on quality.
|
| 192 |
+
|
| 193 |
+
**Some suggestions for improving generation quality:**
|
| 194 |
+
1. Use High-Quality Images
|
| 195 |
+
- Provide clear images, preferably with a resolution **greater than 512×512 pixels**.
|
| 196 |
+
- Small or blurry inputs will result in low-quality outputs.
|
| 197 |
+
2. Be Specific with Instructions
|
| 198 |
+
- Clearly describe both **what to change** and **how you want it changed**.
|
| 199 |
+
- For in-context generation tasks, explicitly state which elements should come from which image. For example, instead of "Add bird to desk", say "Add the bird from image 1 onto the desk in image 2."
|
| 200 |
+
3. Prioritize English
|
| 201 |
+
The model currently performs best with **English** prompts.
|
| 202 |
+
|
| 203 |
+
## 💻 Resources Requirement
|
| 204 |
+
OmniGen2 natively requires an **NVIDIA RTX 3090** or an equivalent GPU with approximately **17GB of VRAM**. For devices with less VRAM, you can enable **CPU Offload** to run the model.
|
| 205 |
+
|
| 206 |
+
**Performance Tip**: To improve inference speed, consider decreasing the `cfg_range_end` parameter. Within a reasonable range, this has a negligible impact on output quality.
|
| 207 |
+
|
| 208 |
+
The following table details the inference performance of OmniGen2 on an **A800 GPU**:
|
| 209 |
+
<p align="center">
|
| 210 |
+
<img src="assets/efficiency.png" width="95%">
|
| 211 |
+
<br>
|
| 212 |
+
<em>Inference Efficiency of OmniGen2.</em>
|
| 213 |
+
</p>
|
| 214 |
+
|
| 215 |
+
## ❤️ Citing Us
|
| 216 |
+
If you find this repository or our work useful, please consider giving a star ⭐ and citation 🦖, which would be greatly appreciated (OmniGen2 report will be available as soon as possible):
|
| 217 |
+
|
| 218 |
+
```bibtex
|
| 219 |
+
@article{wu2025omnigen2,
|
| 220 |
+
title={OmniGen2: Exploration to Advanced Multimodal Generation},
|
| 221 |
+
author={Chenyuan Wu and Pengfei Zheng and Ruiran Yan and Shitao Xiao and Xin Luo and Yueze Wang and Wanli Li and Xiyan Jiang and Yexin Liu and Junjie Zhou and Ze Liu and Ziyi Xia and Chaofan Li and Haoge Deng and Jiahao Wang and Kun Luo and Bo Zhang and Defu Lian and Xinlong Wang and Zhongyuan Wang and Tiejun Huang and Zheng Liu},
|
| 222 |
+
journal={arXiv preprint arXiv:2506.18871},
|
| 223 |
+
year={2025}
|
| 224 |
+
}
|
| 225 |
+
```
|
| 226 |
+
|
| 227 |
+
## License
|
| 228 |
+
This work is licensed under Apache 2.0 license.
|
assets/brand.png
ADDED
|
Git LFS Details
|
assets/efficiency.png
ADDED
|
Git LFS Details
|
assets/examples_edit.png
ADDED
|
Git LFS Details
|
assets/examples_subject.png
ADDED
|
Git LFS Details
|
assets/teaser.jpg
ADDED
|
Git LFS Details
|
assets/teaser.png
ADDED
|
Git LFS Details
|
mllm/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"image_token_id": 151655,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 128000,
|
| 14 |
+
"max_window_layers": 70,
|
| 15 |
+
"model_type": "qwen2_5_vl",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 36,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"video_token_id": 151656,
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"depth": 32,
|
| 39 |
+
"fullatt_block_indexes": [
|
| 40 |
+
7,
|
| 41 |
+
15,
|
| 42 |
+
23,
|
| 43 |
+
31
|
| 44 |
+
],
|
| 45 |
+
"hidden_act": "silu",
|
| 46 |
+
"hidden_size": 1280,
|
| 47 |
+
"in_channels": 3,
|
| 48 |
+
"in_chans": 3,
|
| 49 |
+
"intermediate_size": 3420,
|
| 50 |
+
"model_type": "qwen2_5_vl",
|
| 51 |
+
"num_heads": 16,
|
| 52 |
+
"out_hidden_size": 2048,
|
| 53 |
+
"patch_size": 14,
|
| 54 |
+
"spatial_merge_size": 2,
|
| 55 |
+
"spatial_patch_size": 14,
|
| 56 |
+
"temporal_patch_size": 2,
|
| 57 |
+
"tokens_per_second": 2,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"window_size": 112
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652,
|
| 63 |
+
"vision_token_id": 151654,
|
| 64 |
+
"vocab_size": 151936
|
| 65 |
+
}
|
mllm/generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation": "flash_attention_2",
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"repetition_penalty": 1.05,
|
| 11 |
+
"temperature": 0.1,
|
| 12 |
+
"top_k": 1,
|
| 13 |
+
"top_p": 0.001,
|
| 14 |
+
"transformers_version": "4.51.3"
|
| 15 |
+
}
|
mllm/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfe5503539cf9335017bca96cd4409cec234de71af6bbe9a6035c0952e9319c2
|
| 3 |
+
size 4972304384
|
mllm/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b6f098d029dd4fadcc032d2d9da1914204d098c04a5a38f19bba23beb3039c
|
| 3 |
+
size 4932949248
|
mllm/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa99a4bf5f586e0f6aa2e941a66283afc98df2a8c726496f717ff7939ec70651
|
| 3 |
+
size 4932949336
|
mllm/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9bdab213ea510b2de9805ae054076d804fe578eb052460ed7988c8cc3aee114
|
| 3 |
+
size 180380208
|
mllm/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,831 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 15018491904
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 151 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 263 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 264 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 271 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 272 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 273 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 284 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 285 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 287 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 331 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 332 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 333 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 334 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 336 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 343 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 344 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 345 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 346 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 347 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 348 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 355 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 356 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 357 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 358 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 359 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 360 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 367 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 368 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 370 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 406 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 407 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 408 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 409 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 415 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 416 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 417 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 418 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 419 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 420 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 421 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 427 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 428 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 429 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 430 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 431 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 432 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 433 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 439 |
+
"model.norm.weight": "model-00004-of-00004.safetensors",
|
| 440 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 441 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 451 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 453 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 463 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 465 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 475 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 477 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 487 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 489 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 490 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 491 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 493 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 497 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 499 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 501 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 505 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 507 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 509 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 511 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 513 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 515 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 517 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 519 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 523 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 525 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 527 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 531 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 533 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 535 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 537 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 545 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 547 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 549 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 553 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 557 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 558 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 559 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 561 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 562 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 563 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 565 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 566 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 569 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 570 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 571 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 573 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 574 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 575 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 576 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 577 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 579 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 581 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 583 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 585 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 587 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 589 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 591 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 593 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 597 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 599 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 601 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 603 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 605 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 609 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 615 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 621 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 623 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 625 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 627 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 631 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 633 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 641 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 645 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 647 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 649 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 653 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 654 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 657 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 659 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 661 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 663 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 669 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 671 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 672 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 673 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 674 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 676 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 678 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 679 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 681 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 682 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 684 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 687 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 688 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 689 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
| 691 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 693 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 696 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 697 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 698 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 700 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 701 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
| 703 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 705 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 706 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 707 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 709 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 711 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 712 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 713 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 714 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
| 715 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 717 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 719 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 720 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 721 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 722 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 723 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 724 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 727 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 729 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 731 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 732 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 733 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 734 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 735 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 736 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 737 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 738 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
| 739 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
| 740 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 741 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 743 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 745 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 747 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 748 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 749 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 750 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
| 751 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
| 752 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 753 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 756 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 757 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 758 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 759 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 760 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 761 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 762 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 763 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 764 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 765 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 766 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 767 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 768 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 769 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 770 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 771 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 772 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 773 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 774 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 775 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 776 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 777 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 778 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 779 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 780 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 781 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 782 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 783 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 784 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 785 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 786 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 787 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 788 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 789 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 790 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 791 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 792 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 793 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 794 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 795 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 796 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 797 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 798 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 799 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 800 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 801 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 802 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 803 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 804 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 805 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 806 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 807 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 808 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 809 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 810 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 811 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 812 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 813 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 814 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 815 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 816 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
| 817 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 818 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
| 819 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 820 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
| 821 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 822 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 823 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 824 |
+
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
| 825 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
| 826 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
| 827 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
| 828 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
| 829 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
|
| 830 |
+
}
|
| 831 |
+
}
|
mllm_processor/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endofimg|>": 151666,
|
| 7 |
+
"<|endofmeta|>": 151668,
|
| 8 |
+
"<|endoftext|>": 151643,
|
| 9 |
+
"<|file_sep|>": 151664,
|
| 10 |
+
"<|fim_middle|>": 151660,
|
| 11 |
+
"<|fim_pad|>": 151662,
|
| 12 |
+
"<|fim_prefix|>": 151659,
|
| 13 |
+
"<|fim_suffix|>": 151661,
|
| 14 |
+
"<|im_end|>": 151645,
|
| 15 |
+
"<|im_start|>": 151644,
|
| 16 |
+
"<|image_pad|>": 151655,
|
| 17 |
+
"<|img|>": 151665,
|
| 18 |
+
"<|meta|>": 151667,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
mllm_processor/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
mllm_processor/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mllm_processor/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
mllm_processor/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
mllm_processor/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69f12bcc978e3d112e092478b218f0161ef3d4bec08792866c99d29830772f08
|
| 3 |
+
size 11422644
|
mllm_processor/tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|img|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "<|endofimg|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<|meta|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "<|endofmeta|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 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 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\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' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\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",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
mllm_processor/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model_index.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "OmniGen2Pipeline",
|
| 3 |
+
"_diffusers_version": "0.33.1",
|
| 4 |
+
"mllm": [
|
| 5 |
+
"transformers",
|
| 6 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"processor": [
|
| 9 |
+
"transformers",
|
| 10 |
+
"Qwen2_5_VLProcessor"
|
| 11 |
+
],
|
| 12 |
+
"scheduler": [
|
| 13 |
+
"scheduling_flow_match_euler_discrete",
|
| 14 |
+
"FlowMatchEulerDiscreteScheduler"
|
| 15 |
+
],
|
| 16 |
+
"transformer": [
|
| 17 |
+
"transformer_omnigen2",
|
| 18 |
+
"OmniGen2Transformer2DModel"
|
| 19 |
+
],
|
| 20 |
+
"vae": [
|
| 21 |
+
"diffusers",
|
| 22 |
+
"AutoencoderKL"
|
| 23 |
+
]
|
| 24 |
+
}
|
processor/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endofimg|>": 151666,
|
| 7 |
+
"<|endofmeta|>": 151668,
|
| 8 |
+
"<|endoftext|>": 151643,
|
| 9 |
+
"<|file_sep|>": 151664,
|
| 10 |
+
"<|fim_middle|>": 151660,
|
| 11 |
+
"<|fim_pad|>": 151662,
|
| 12 |
+
"<|fim_prefix|>": 151659,
|
| 13 |
+
"<|fim_suffix|>": 151661,
|
| 14 |
+
"<|im_end|>": 151645,
|
| 15 |
+
"<|im_start|>": 151644,
|
| 16 |
+
"<|image_pad|>": 151655,
|
| 17 |
+
"<|img|>": 151665,
|
| 18 |
+
"<|meta|>": 151667,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
processor/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
processor/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
processor/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
processor/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69f12bcc978e3d112e092478b218f0161ef3d4bec08792866c99d29830772f08
|
| 3 |
+
size 11422644
|
processor/tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|img|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "<|endofimg|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<|meta|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "<|endofmeta|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 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 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\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' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\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",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
processor/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
scheduler/__pycache__/scheduling_flow_match_euler_discrete.cpython-310.pyc
ADDED
|
Binary file (7.68 kB). View file
|
|
|
scheduler/__pycache__/scheduling_flow_match_euler_discrete.cpython-311.pyc
ADDED
|
Binary file (10.3 kB). View file
|
|
|
scheduler/__pycache__/scheduling_flow_match_euler_discrete.cpython-312.pyc
ADDED
|
Binary file (9.95 kB). View file
|
|
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.33.1",
|
| 4 |
+
"dynamic_time_shift": true,
|
| 5 |
+
"num_train_timesteps": 1000
|
| 6 |
+
}
|
scheduler/scheduling_flow_match_euler_discrete.py
ADDED
|
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Copyright 2024 Stability AI, Katherine Crowson and The HuggingFace Team. All rights reserved.
|
| 2 |
+
#
|
| 3 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 4 |
+
# you may not use this file except in compliance with the License.
|
| 5 |
+
# You may obtain a copy of the License at
|
| 6 |
+
#
|
| 7 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 8 |
+
#
|
| 9 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 10 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 11 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 12 |
+
# See the License for the specific language governing permissions and
|
| 13 |
+
# limitations under the License.
|
| 14 |
+
|
| 15 |
+
import math
|
| 16 |
+
from dataclasses import dataclass
|
| 17 |
+
from typing import List, Optional, Tuple, Union
|
| 18 |
+
|
| 19 |
+
import numpy as np
|
| 20 |
+
import torch
|
| 21 |
+
|
| 22 |
+
from diffusers.configuration_utils import ConfigMixin, register_to_config
|
| 23 |
+
from diffusers.utils import BaseOutput, logging
|
| 24 |
+
from diffusers.schedulers.scheduling_utils import SchedulerMixin
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
logger = logging.get_logger(__name__) # pylint: disable=invalid-name
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
@dataclass
|
| 31 |
+
class FlowMatchEulerDiscreteSchedulerOutput(BaseOutput):
|
| 32 |
+
"""
|
| 33 |
+
Output class for the scheduler's `step` function output.
|
| 34 |
+
|
| 35 |
+
Args:
|
| 36 |
+
prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
|
| 37 |
+
Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
|
| 38 |
+
denoising loop.
|
| 39 |
+
"""
|
| 40 |
+
|
| 41 |
+
prev_sample: torch.FloatTensor
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
class FlowMatchEulerDiscreteScheduler(SchedulerMixin, ConfigMixin):
|
| 45 |
+
"""
|
| 46 |
+
Euler scheduler.
|
| 47 |
+
|
| 48 |
+
This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
|
| 49 |
+
methods the library implements for all schedulers such as loading and saving.
|
| 50 |
+
|
| 51 |
+
Args:
|
| 52 |
+
num_train_timesteps (`int`, defaults to 1000):
|
| 53 |
+
The number of diffusion steps to train the model.
|
| 54 |
+
timestep_spacing (`str`, defaults to `"linspace"`):
|
| 55 |
+
The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
|
| 56 |
+
Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
|
| 57 |
+
shift (`float`, defaults to 1.0):
|
| 58 |
+
The shift value for the timestep schedule.
|
| 59 |
+
"""
|
| 60 |
+
|
| 61 |
+
_compatibles = []
|
| 62 |
+
order = 1
|
| 63 |
+
|
| 64 |
+
@register_to_config
|
| 65 |
+
def __init__(
|
| 66 |
+
self,
|
| 67 |
+
num_train_timesteps: int = 1000,
|
| 68 |
+
dynamic_time_shift: bool = False
|
| 69 |
+
):
|
| 70 |
+
timesteps = torch.linspace(0, 1, num_train_timesteps + 1, dtype=torch.float32)[:-1]
|
| 71 |
+
|
| 72 |
+
self.timesteps = timesteps
|
| 73 |
+
|
| 74 |
+
self._step_index = None
|
| 75 |
+
self._begin_index = None
|
| 76 |
+
|
| 77 |
+
@property
|
| 78 |
+
def step_index(self):
|
| 79 |
+
"""
|
| 80 |
+
The index counter for current timestep. It will increase 1 after each scheduler step.
|
| 81 |
+
"""
|
| 82 |
+
return self._step_index
|
| 83 |
+
|
| 84 |
+
@property
|
| 85 |
+
def begin_index(self):
|
| 86 |
+
"""
|
| 87 |
+
The index for the first timestep. It should be set from pipeline with `set_begin_index` method.
|
| 88 |
+
"""
|
| 89 |
+
return self._begin_index
|
| 90 |
+
|
| 91 |
+
# Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.set_begin_index
|
| 92 |
+
def set_begin_index(self, begin_index: int = 0):
|
| 93 |
+
"""
|
| 94 |
+
Sets the begin index for the scheduler. This function should be run from pipeline before the inference.
|
| 95 |
+
|
| 96 |
+
Args:
|
| 97 |
+
begin_index (`int`):
|
| 98 |
+
The begin index for the scheduler.
|
| 99 |
+
"""
|
| 100 |
+
self._begin_index = begin_index
|
| 101 |
+
|
| 102 |
+
def index_for_timestep(self, timestep, schedule_timesteps=None):
|
| 103 |
+
if schedule_timesteps is None:
|
| 104 |
+
schedule_timesteps = self._timesteps
|
| 105 |
+
|
| 106 |
+
indices = (schedule_timesteps == timestep).nonzero()
|
| 107 |
+
|
| 108 |
+
# The sigma index that is taken for the **very** first `step`
|
| 109 |
+
# is always the second index (or the last index if there is only 1)
|
| 110 |
+
# This way we can ensure we don't accidentally skip a sigma in
|
| 111 |
+
# case we start in the middle of the denoising schedule (e.g. for image-to-image)
|
| 112 |
+
pos = 1 if len(indices) > 1 else 0
|
| 113 |
+
|
| 114 |
+
return indices[pos].item()
|
| 115 |
+
|
| 116 |
+
# def time_shift(self, mu: float, sigma: float, t: torch.Tensor):
|
| 117 |
+
# return math.exp(mu) / (math.exp(mu) + (1 / t - 1) ** sigma)
|
| 118 |
+
|
| 119 |
+
def set_timesteps(
|
| 120 |
+
self,
|
| 121 |
+
num_inference_steps: int = None,
|
| 122 |
+
device: Union[str, torch.device] = None,
|
| 123 |
+
timesteps: Optional[List[float]] = None,
|
| 124 |
+
num_tokens: Optional[int] = None
|
| 125 |
+
):
|
| 126 |
+
"""
|
| 127 |
+
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
|
| 128 |
+
|
| 129 |
+
Args:
|
| 130 |
+
num_inference_steps (`int`):
|
| 131 |
+
The number of diffusion steps used when generating samples with a pre-trained model.
|
| 132 |
+
device (`str` or `torch.device`, *optional*):
|
| 133 |
+
The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
|
| 134 |
+
"""
|
| 135 |
+
|
| 136 |
+
if timesteps is None:
|
| 137 |
+
self.num_inference_steps = num_inference_steps
|
| 138 |
+
timesteps = np.linspace(0, 1, num_inference_steps + 1, dtype=np.float32)[:-1]
|
| 139 |
+
if self.config.dynamic_time_shift and num_tokens is not None:
|
| 140 |
+
m = np.sqrt(num_tokens) / 40 # when input resolution is 320 * 320, m = 1, when input resolution is 1024 * 1024, m = 3.2
|
| 141 |
+
timesteps = timesteps / (m - m * timesteps + timesteps)
|
| 142 |
+
|
| 143 |
+
timesteps = torch.from_numpy(timesteps).to(dtype=torch.float32, device=device)
|
| 144 |
+
_timesteps = torch.cat([timesteps, torch.ones(1, device=timesteps.device)])
|
| 145 |
+
|
| 146 |
+
self.timesteps = timesteps
|
| 147 |
+
self._timesteps = _timesteps
|
| 148 |
+
self._step_index = None
|
| 149 |
+
self._begin_index = None
|
| 150 |
+
|
| 151 |
+
def _init_step_index(self, timestep):
|
| 152 |
+
if self.begin_index is None:
|
| 153 |
+
if isinstance(timestep, torch.Tensor):
|
| 154 |
+
timestep = timestep.to(self.timesteps.device)
|
| 155 |
+
self._step_index = self.index_for_timestep(timestep)
|
| 156 |
+
else:
|
| 157 |
+
self._step_index = self._begin_index
|
| 158 |
+
|
| 159 |
+
def step(
|
| 160 |
+
self,
|
| 161 |
+
model_output: torch.FloatTensor,
|
| 162 |
+
timestep: Union[float, torch.FloatTensor],
|
| 163 |
+
sample: torch.FloatTensor,
|
| 164 |
+
generator: Optional[torch.Generator] = None,
|
| 165 |
+
return_dict: bool = True,
|
| 166 |
+
) -> Union[FlowMatchEulerDiscreteSchedulerOutput, Tuple]:
|
| 167 |
+
"""
|
| 168 |
+
Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
|
| 169 |
+
process from the learned model outputs (most often the predicted noise).
|
| 170 |
+
|
| 171 |
+
Args:
|
| 172 |
+
model_output (`torch.FloatTensor`):
|
| 173 |
+
The direct output from learned diffusion model.
|
| 174 |
+
timestep (`float`):
|
| 175 |
+
The current discrete timestep in the diffusion chain.
|
| 176 |
+
sample (`torch.FloatTensor`):
|
| 177 |
+
A current instance of a sample created by the diffusion process.
|
| 178 |
+
s_churn (`float`):
|
| 179 |
+
s_tmin (`float`):
|
| 180 |
+
s_tmax (`float`):
|
| 181 |
+
s_noise (`float`, defaults to 1.0):
|
| 182 |
+
Scaling factor for noise added to the sample.
|
| 183 |
+
generator (`torch.Generator`, *optional*):
|
| 184 |
+
A random number generator.
|
| 185 |
+
return_dict (`bool`):
|
| 186 |
+
Whether or not to return a [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or
|
| 187 |
+
tuple.
|
| 188 |
+
|
| 189 |
+
Returns:
|
| 190 |
+
[`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or `tuple`:
|
| 191 |
+
If return_dict is `True`, [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] is
|
| 192 |
+
returned, otherwise a tuple is returned where the first element is the sample tensor.
|
| 193 |
+
"""
|
| 194 |
+
|
| 195 |
+
if (
|
| 196 |
+
isinstance(timestep, int)
|
| 197 |
+
or isinstance(timestep, torch.IntTensor)
|
| 198 |
+
or isinstance(timestep, torch.LongTensor)
|
| 199 |
+
):
|
| 200 |
+
raise ValueError(
|
| 201 |
+
(
|
| 202 |
+
"Passing integer indices (e.g. from `enumerate(timesteps)`) as timesteps to"
|
| 203 |
+
" `EulerDiscreteScheduler.step()` is not supported. Make sure to pass"
|
| 204 |
+
" one of the `scheduler.timesteps` as a timestep."
|
| 205 |
+
),
|
| 206 |
+
)
|
| 207 |
+
|
| 208 |
+
if self.step_index is None:
|
| 209 |
+
self._init_step_index(timestep)
|
| 210 |
+
# Upcast to avoid precision issues when computing prev_sample
|
| 211 |
+
sample = sample.to(torch.float32)
|
| 212 |
+
t = self._timesteps[self.step_index]
|
| 213 |
+
t_next = self._timesteps[self.step_index + 1]
|
| 214 |
+
|
| 215 |
+
prev_sample = sample + (t_next - t) * model_output
|
| 216 |
+
|
| 217 |
+
# Cast sample back to model compatible dtype
|
| 218 |
+
prev_sample = prev_sample.to(model_output.dtype)
|
| 219 |
+
|
| 220 |
+
# upon completion increase step index by one
|
| 221 |
+
self._step_index += 1
|
| 222 |
+
|
| 223 |
+
if not return_dict:
|
| 224 |
+
return (prev_sample,)
|
| 225 |
+
|
| 226 |
+
return FlowMatchEulerDiscreteSchedulerOutput(prev_sample=prev_sample)
|
| 227 |
+
|
| 228 |
+
def __len__(self):
|
| 229 |
+
return self.config.num_train_timesteps
|
time_caption_context_reinit/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "OmniGen2Transformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"axes_dim_rope": [
|
| 5 |
+
40,
|
| 6 |
+
40,
|
| 7 |
+
40
|
| 8 |
+
],
|
| 9 |
+
"axes_lens": [
|
| 10 |
+
10000,
|
| 11 |
+
10000,
|
| 12 |
+
10000
|
| 13 |
+
],
|
| 14 |
+
"ffn_dim_multiplier": null,
|
| 15 |
+
"hidden_size": 2520,
|
| 16 |
+
"in_channels": 16,
|
| 17 |
+
"multiple_of": 256,
|
| 18 |
+
"norm_eps": 1e-05,
|
| 19 |
+
"num_attention_heads": 21,
|
| 20 |
+
"num_kv_heads": 7,
|
| 21 |
+
"num_layers": 32,
|
| 22 |
+
"num_refiner_layers": 2,
|
| 23 |
+
"out_channels": null,
|
| 24 |
+
"patch_size": 2,
|
| 25 |
+
"text_feat_dim": 3584,
|
| 26 |
+
"timestep_scale": 1000
|
| 27 |
+
}
|
time_caption_context_reinit/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb80cc5bd00e6cc7e8c18d74342872b6de1c7f33fc34f5ab147d1d4bf5bd10da
|
| 3 |
+
size 9969124696
|
time_caption_context_reinit/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d22479336b8e493506d13dea6c4d0ebadc94b0734e1a465ffc8023113733a45
|
| 3 |
+
size 5915071312
|
time_caption_context_reinit/diffusion_pytorch_model.safetensors.index.json
ADDED
|
@@ -0,0 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 15884134624
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"context_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 7 |
+
"context_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 8 |
+
"context_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 9 |
+
"context_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 10 |
+
"context_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 11 |
+
"context_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 12 |
+
"context_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 13 |
+
"context_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 14 |
+
"context_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 15 |
+
"context_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 16 |
+
"context_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 17 |
+
"context_refiner.0.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 18 |
+
"context_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 19 |
+
"context_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 20 |
+
"context_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 21 |
+
"context_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 22 |
+
"context_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 23 |
+
"context_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 24 |
+
"context_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 25 |
+
"context_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 26 |
+
"context_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 27 |
+
"context_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 28 |
+
"context_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 29 |
+
"context_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 30 |
+
"context_refiner.1.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 31 |
+
"context_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 32 |
+
"image_index_embedding": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 33 |
+
"layers.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 34 |
+
"layers.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 35 |
+
"layers.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 36 |
+
"layers.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 37 |
+
"layers.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 38 |
+
"layers.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 39 |
+
"layers.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 40 |
+
"layers.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 41 |
+
"layers.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 42 |
+
"layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 43 |
+
"layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 44 |
+
"layers.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 45 |
+
"layers.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 46 |
+
"layers.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 47 |
+
"layers.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 48 |
+
"layers.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 49 |
+
"layers.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 50 |
+
"layers.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 51 |
+
"layers.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 52 |
+
"layers.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 53 |
+
"layers.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 54 |
+
"layers.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 55 |
+
"layers.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 56 |
+
"layers.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 57 |
+
"layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 58 |
+
"layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 59 |
+
"layers.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 60 |
+
"layers.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 61 |
+
"layers.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 62 |
+
"layers.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 63 |
+
"layers.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 64 |
+
"layers.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 65 |
+
"layers.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 66 |
+
"layers.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 67 |
+
"layers.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 68 |
+
"layers.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 69 |
+
"layers.10.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 70 |
+
"layers.10.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 71 |
+
"layers.10.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 72 |
+
"layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 73 |
+
"layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 74 |
+
"layers.10.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 75 |
+
"layers.10.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 76 |
+
"layers.10.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 77 |
+
"layers.10.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 78 |
+
"layers.11.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 79 |
+
"layers.11.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 80 |
+
"layers.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 81 |
+
"layers.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 82 |
+
"layers.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 83 |
+
"layers.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 84 |
+
"layers.11.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 85 |
+
"layers.11.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 86 |
+
"layers.11.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 87 |
+
"layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 88 |
+
"layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 89 |
+
"layers.11.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 90 |
+
"layers.11.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 91 |
+
"layers.11.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 92 |
+
"layers.11.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 93 |
+
"layers.12.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 94 |
+
"layers.12.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 95 |
+
"layers.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 96 |
+
"layers.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 97 |
+
"layers.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 98 |
+
"layers.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 99 |
+
"layers.12.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 100 |
+
"layers.12.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 101 |
+
"layers.12.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 102 |
+
"layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 103 |
+
"layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 104 |
+
"layers.12.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 105 |
+
"layers.12.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 106 |
+
"layers.12.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 107 |
+
"layers.12.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 108 |
+
"layers.13.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 109 |
+
"layers.13.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 110 |
+
"layers.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 111 |
+
"layers.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 112 |
+
"layers.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 113 |
+
"layers.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 114 |
+
"layers.13.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 115 |
+
"layers.13.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 116 |
+
"layers.13.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 117 |
+
"layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 118 |
+
"layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 119 |
+
"layers.13.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 120 |
+
"layers.13.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 121 |
+
"layers.13.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 122 |
+
"layers.13.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 123 |
+
"layers.14.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 124 |
+
"layers.14.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 125 |
+
"layers.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 126 |
+
"layers.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 127 |
+
"layers.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 128 |
+
"layers.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 129 |
+
"layers.14.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 130 |
+
"layers.14.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 131 |
+
"layers.14.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 132 |
+
"layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 133 |
+
"layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 134 |
+
"layers.14.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 135 |
+
"layers.14.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 136 |
+
"layers.14.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 137 |
+
"layers.14.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 138 |
+
"layers.15.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 139 |
+
"layers.15.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 140 |
+
"layers.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 141 |
+
"layers.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 142 |
+
"layers.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 143 |
+
"layers.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 144 |
+
"layers.15.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 145 |
+
"layers.15.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 146 |
+
"layers.15.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 147 |
+
"layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 148 |
+
"layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 149 |
+
"layers.15.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 150 |
+
"layers.15.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 151 |
+
"layers.15.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 152 |
+
"layers.15.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 153 |
+
"layers.16.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 154 |
+
"layers.16.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 155 |
+
"layers.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 156 |
+
"layers.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 157 |
+
"layers.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 158 |
+
"layers.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 159 |
+
"layers.16.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 160 |
+
"layers.16.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 161 |
+
"layers.16.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 162 |
+
"layers.16.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 163 |
+
"layers.16.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 164 |
+
"layers.16.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 165 |
+
"layers.16.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 166 |
+
"layers.16.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 167 |
+
"layers.16.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 168 |
+
"layers.17.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 169 |
+
"layers.17.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 170 |
+
"layers.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 171 |
+
"layers.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 172 |
+
"layers.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 173 |
+
"layers.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 174 |
+
"layers.17.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 175 |
+
"layers.17.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 176 |
+
"layers.17.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 177 |
+
"layers.17.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 178 |
+
"layers.17.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 179 |
+
"layers.17.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 180 |
+
"layers.17.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 181 |
+
"layers.17.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 182 |
+
"layers.17.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 183 |
+
"layers.18.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 184 |
+
"layers.18.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 185 |
+
"layers.18.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 186 |
+
"layers.18.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 187 |
+
"layers.18.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 188 |
+
"layers.18.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 189 |
+
"layers.18.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 190 |
+
"layers.18.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 191 |
+
"layers.18.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 192 |
+
"layers.18.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 193 |
+
"layers.18.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 194 |
+
"layers.18.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 195 |
+
"layers.18.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 196 |
+
"layers.18.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 197 |
+
"layers.18.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 198 |
+
"layers.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 199 |
+
"layers.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 200 |
+
"layers.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 201 |
+
"layers.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 202 |
+
"layers.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 203 |
+
"layers.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 204 |
+
"layers.19.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 205 |
+
"layers.19.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 206 |
+
"layers.19.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 207 |
+
"layers.19.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 208 |
+
"layers.19.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 209 |
+
"layers.19.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 210 |
+
"layers.19.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 211 |
+
"layers.19.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 212 |
+
"layers.19.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 213 |
+
"layers.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 214 |
+
"layers.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 215 |
+
"layers.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 216 |
+
"layers.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 217 |
+
"layers.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 218 |
+
"layers.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 219 |
+
"layers.2.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 220 |
+
"layers.2.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 221 |
+
"layers.2.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 222 |
+
"layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 223 |
+
"layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 224 |
+
"layers.2.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 225 |
+
"layers.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 226 |
+
"layers.2.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 227 |
+
"layers.2.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 228 |
+
"layers.20.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 229 |
+
"layers.20.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 230 |
+
"layers.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 231 |
+
"layers.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 232 |
+
"layers.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 233 |
+
"layers.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 234 |
+
"layers.20.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 235 |
+
"layers.20.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 236 |
+
"layers.20.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 237 |
+
"layers.20.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 238 |
+
"layers.20.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 239 |
+
"layers.20.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 240 |
+
"layers.20.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 241 |
+
"layers.20.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 242 |
+
"layers.20.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 243 |
+
"layers.21.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 244 |
+
"layers.21.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 245 |
+
"layers.21.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 246 |
+
"layers.21.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 247 |
+
"layers.21.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 248 |
+
"layers.21.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 249 |
+
"layers.21.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 250 |
+
"layers.21.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 251 |
+
"layers.21.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 252 |
+
"layers.21.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 253 |
+
"layers.21.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 254 |
+
"layers.21.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 255 |
+
"layers.21.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 256 |
+
"layers.21.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 257 |
+
"layers.21.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 258 |
+
"layers.22.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 259 |
+
"layers.22.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 260 |
+
"layers.22.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 261 |
+
"layers.22.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 262 |
+
"layers.22.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 263 |
+
"layers.22.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 264 |
+
"layers.22.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 265 |
+
"layers.22.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 266 |
+
"layers.22.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 267 |
+
"layers.22.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 268 |
+
"layers.22.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 269 |
+
"layers.22.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 270 |
+
"layers.22.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 271 |
+
"layers.22.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 272 |
+
"layers.22.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 273 |
+
"layers.23.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 274 |
+
"layers.23.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 275 |
+
"layers.23.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 276 |
+
"layers.23.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 277 |
+
"layers.23.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 278 |
+
"layers.23.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 279 |
+
"layers.23.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 280 |
+
"layers.23.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 281 |
+
"layers.23.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 282 |
+
"layers.23.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 283 |
+
"layers.23.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 284 |
+
"layers.23.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 285 |
+
"layers.23.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 286 |
+
"layers.23.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 287 |
+
"layers.23.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 288 |
+
"layers.24.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 289 |
+
"layers.24.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 290 |
+
"layers.24.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 291 |
+
"layers.24.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 292 |
+
"layers.24.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 293 |
+
"layers.24.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 294 |
+
"layers.24.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 295 |
+
"layers.24.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 296 |
+
"layers.24.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 297 |
+
"layers.24.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 298 |
+
"layers.24.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 299 |
+
"layers.24.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 300 |
+
"layers.24.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 301 |
+
"layers.24.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 302 |
+
"layers.24.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 303 |
+
"layers.25.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 304 |
+
"layers.25.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 305 |
+
"layers.25.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 306 |
+
"layers.25.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 307 |
+
"layers.25.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 308 |
+
"layers.25.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 309 |
+
"layers.25.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 310 |
+
"layers.25.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 311 |
+
"layers.25.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 312 |
+
"layers.25.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 313 |
+
"layers.25.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 314 |
+
"layers.25.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 315 |
+
"layers.25.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 316 |
+
"layers.25.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 317 |
+
"layers.25.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 318 |
+
"layers.26.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 319 |
+
"layers.26.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 320 |
+
"layers.26.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 321 |
+
"layers.26.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 322 |
+
"layers.26.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 323 |
+
"layers.26.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 324 |
+
"layers.26.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 325 |
+
"layers.26.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 326 |
+
"layers.26.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 327 |
+
"layers.26.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 328 |
+
"layers.26.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 329 |
+
"layers.26.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 330 |
+
"layers.26.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 331 |
+
"layers.26.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 332 |
+
"layers.26.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 333 |
+
"layers.27.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 334 |
+
"layers.27.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 335 |
+
"layers.27.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 336 |
+
"layers.27.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 337 |
+
"layers.27.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 338 |
+
"layers.27.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 339 |
+
"layers.27.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 340 |
+
"layers.27.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 341 |
+
"layers.27.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 342 |
+
"layers.27.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 343 |
+
"layers.27.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 344 |
+
"layers.27.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 345 |
+
"layers.27.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 346 |
+
"layers.27.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 347 |
+
"layers.27.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 348 |
+
"layers.28.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 349 |
+
"layers.28.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 350 |
+
"layers.28.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 351 |
+
"layers.28.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 352 |
+
"layers.28.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 353 |
+
"layers.28.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 354 |
+
"layers.28.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 355 |
+
"layers.28.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 356 |
+
"layers.28.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 357 |
+
"layers.28.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 358 |
+
"layers.28.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 359 |
+
"layers.28.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 360 |
+
"layers.28.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 361 |
+
"layers.28.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 362 |
+
"layers.28.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 363 |
+
"layers.29.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 364 |
+
"layers.29.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 365 |
+
"layers.29.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 366 |
+
"layers.29.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 367 |
+
"layers.29.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 368 |
+
"layers.29.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 369 |
+
"layers.29.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 370 |
+
"layers.29.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 371 |
+
"layers.29.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 372 |
+
"layers.29.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 373 |
+
"layers.29.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 374 |
+
"layers.29.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 375 |
+
"layers.29.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 376 |
+
"layers.29.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 377 |
+
"layers.29.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 378 |
+
"layers.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 379 |
+
"layers.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 380 |
+
"layers.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 381 |
+
"layers.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 382 |
+
"layers.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 383 |
+
"layers.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 384 |
+
"layers.3.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 385 |
+
"layers.3.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 386 |
+
"layers.3.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 387 |
+
"layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 388 |
+
"layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 389 |
+
"layers.3.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 390 |
+
"layers.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 391 |
+
"layers.3.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 392 |
+
"layers.3.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 393 |
+
"layers.30.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 394 |
+
"layers.30.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 395 |
+
"layers.30.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 396 |
+
"layers.30.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 397 |
+
"layers.30.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 398 |
+
"layers.30.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 399 |
+
"layers.30.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 400 |
+
"layers.30.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 401 |
+
"layers.30.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 402 |
+
"layers.30.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 403 |
+
"layers.30.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 404 |
+
"layers.30.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 405 |
+
"layers.30.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 406 |
+
"layers.30.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 407 |
+
"layers.30.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 408 |
+
"layers.31.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 409 |
+
"layers.31.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 410 |
+
"layers.31.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 411 |
+
"layers.31.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 412 |
+
"layers.31.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 413 |
+
"layers.31.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 414 |
+
"layers.31.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 415 |
+
"layers.31.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 416 |
+
"layers.31.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 417 |
+
"layers.31.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 418 |
+
"layers.31.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 419 |
+
"layers.31.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 420 |
+
"layers.31.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 421 |
+
"layers.31.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 422 |
+
"layers.31.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 423 |
+
"layers.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 424 |
+
"layers.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 425 |
+
"layers.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 426 |
+
"layers.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 427 |
+
"layers.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 428 |
+
"layers.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 429 |
+
"layers.4.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 430 |
+
"layers.4.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 431 |
+
"layers.4.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 432 |
+
"layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 433 |
+
"layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 434 |
+
"layers.4.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 435 |
+
"layers.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 436 |
+
"layers.4.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 437 |
+
"layers.4.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 438 |
+
"layers.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 439 |
+
"layers.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 440 |
+
"layers.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 441 |
+
"layers.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 442 |
+
"layers.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 443 |
+
"layers.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 444 |
+
"layers.5.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 445 |
+
"layers.5.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 446 |
+
"layers.5.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 447 |
+
"layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 448 |
+
"layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 449 |
+
"layers.5.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 450 |
+
"layers.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 451 |
+
"layers.5.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 452 |
+
"layers.5.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 453 |
+
"layers.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 454 |
+
"layers.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 455 |
+
"layers.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 456 |
+
"layers.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 457 |
+
"layers.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 458 |
+
"layers.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 459 |
+
"layers.6.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 460 |
+
"layers.6.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 461 |
+
"layers.6.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 462 |
+
"layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 463 |
+
"layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 464 |
+
"layers.6.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 465 |
+
"layers.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 466 |
+
"layers.6.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 467 |
+
"layers.6.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 468 |
+
"layers.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 469 |
+
"layers.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 470 |
+
"layers.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 471 |
+
"layers.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 472 |
+
"layers.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 473 |
+
"layers.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 474 |
+
"layers.7.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 475 |
+
"layers.7.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 476 |
+
"layers.7.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 477 |
+
"layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 478 |
+
"layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 479 |
+
"layers.7.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 480 |
+
"layers.7.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 481 |
+
"layers.7.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 482 |
+
"layers.7.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 483 |
+
"layers.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 484 |
+
"layers.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 485 |
+
"layers.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 486 |
+
"layers.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 487 |
+
"layers.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 488 |
+
"layers.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 489 |
+
"layers.8.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 490 |
+
"layers.8.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 491 |
+
"layers.8.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 492 |
+
"layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 493 |
+
"layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 494 |
+
"layers.8.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 495 |
+
"layers.8.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 496 |
+
"layers.8.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 497 |
+
"layers.8.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 498 |
+
"layers.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 499 |
+
"layers.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 500 |
+
"layers.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 501 |
+
"layers.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 502 |
+
"layers.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 503 |
+
"layers.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 504 |
+
"layers.9.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 505 |
+
"layers.9.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 506 |
+
"layers.9.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 507 |
+
"layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 508 |
+
"layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 509 |
+
"layers.9.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 510 |
+
"layers.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 511 |
+
"layers.9.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 512 |
+
"layers.9.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 513 |
+
"noise_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 514 |
+
"noise_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 515 |
+
"noise_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 516 |
+
"noise_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 517 |
+
"noise_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 518 |
+
"noise_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 519 |
+
"noise_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 520 |
+
"noise_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 521 |
+
"noise_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 522 |
+
"noise_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 523 |
+
"noise_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 524 |
+
"noise_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 525 |
+
"noise_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 526 |
+
"noise_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 527 |
+
"noise_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 528 |
+
"noise_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 529 |
+
"noise_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 530 |
+
"noise_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 531 |
+
"noise_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 532 |
+
"noise_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 533 |
+
"noise_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 534 |
+
"noise_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 535 |
+
"noise_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 536 |
+
"noise_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 537 |
+
"noise_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 538 |
+
"noise_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 539 |
+
"noise_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 540 |
+
"noise_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 541 |
+
"noise_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 542 |
+
"noise_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 543 |
+
"norm_out.linear_1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 544 |
+
"norm_out.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 545 |
+
"norm_out.linear_2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 546 |
+
"norm_out.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 547 |
+
"ref_image_patch_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 548 |
+
"ref_image_patch_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 549 |
+
"ref_image_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 550 |
+
"ref_image_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 551 |
+
"ref_image_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 552 |
+
"ref_image_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 553 |
+
"ref_image_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 554 |
+
"ref_image_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 555 |
+
"ref_image_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 556 |
+
"ref_image_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 557 |
+
"ref_image_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 558 |
+
"ref_image_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 559 |
+
"ref_image_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 560 |
+
"ref_image_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 561 |
+
"ref_image_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 562 |
+
"ref_image_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 563 |
+
"ref_image_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 564 |
+
"ref_image_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 565 |
+
"ref_image_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 566 |
+
"ref_image_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 567 |
+
"ref_image_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 568 |
+
"ref_image_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 569 |
+
"ref_image_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 570 |
+
"ref_image_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 571 |
+
"ref_image_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 572 |
+
"ref_image_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 573 |
+
"ref_image_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 574 |
+
"ref_image_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 575 |
+
"ref_image_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 576 |
+
"ref_image_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 577 |
+
"ref_image_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 578 |
+
"ref_image_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 579 |
+
"time_caption_embed.caption_embedder.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 580 |
+
"time_caption_embed.caption_embedder.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 581 |
+
"time_caption_embed.caption_embedder.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 582 |
+
"time_caption_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 583 |
+
"time_caption_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 584 |
+
"time_caption_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 585 |
+
"time_caption_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 586 |
+
"x_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 587 |
+
"x_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
|
| 588 |
+
}
|
| 589 |
+
}
|
time_caption_reinit/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "OmniGen2Transformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"axes_dim_rope": [
|
| 5 |
+
40,
|
| 6 |
+
40,
|
| 7 |
+
40
|
| 8 |
+
],
|
| 9 |
+
"axes_lens": [
|
| 10 |
+
10000,
|
| 11 |
+
10000,
|
| 12 |
+
10000
|
| 13 |
+
],
|
| 14 |
+
"ffn_dim_multiplier": null,
|
| 15 |
+
"hidden_size": 2520,
|
| 16 |
+
"in_channels": 16,
|
| 17 |
+
"multiple_of": 256,
|
| 18 |
+
"norm_eps": 1e-05,
|
| 19 |
+
"num_attention_heads": 21,
|
| 20 |
+
"num_kv_heads": 7,
|
| 21 |
+
"num_layers": 32,
|
| 22 |
+
"num_refiner_layers": 2,
|
| 23 |
+
"out_channels": null,
|
| 24 |
+
"patch_size": 2,
|
| 25 |
+
"text_feat_dim": 3584,
|
| 26 |
+
"timestep_scale": 1000
|
| 27 |
+
}
|
time_caption_reinit/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b83b1c092eb2ce9f8e32a37f4243b3a9a8c347f77cdd0b38f28d995570f62a
|
| 3 |
+
size 9969124696
|
time_caption_reinit/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d22479336b8e493506d13dea6c4d0ebadc94b0734e1a465ffc8023113733a45
|
| 3 |
+
size 5915071312
|
time_caption_reinit/diffusion_pytorch_model.safetensors.index.json
ADDED
|
@@ -0,0 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 15884134624
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"context_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 7 |
+
"context_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 8 |
+
"context_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 9 |
+
"context_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 10 |
+
"context_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 11 |
+
"context_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 12 |
+
"context_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 13 |
+
"context_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 14 |
+
"context_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 15 |
+
"context_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 16 |
+
"context_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 17 |
+
"context_refiner.0.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 18 |
+
"context_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 19 |
+
"context_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 20 |
+
"context_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 21 |
+
"context_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 22 |
+
"context_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 23 |
+
"context_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 24 |
+
"context_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 25 |
+
"context_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 26 |
+
"context_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 27 |
+
"context_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 28 |
+
"context_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 29 |
+
"context_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 30 |
+
"context_refiner.1.norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 31 |
+
"context_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 32 |
+
"image_index_embedding": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 33 |
+
"layers.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 34 |
+
"layers.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 35 |
+
"layers.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 36 |
+
"layers.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 37 |
+
"layers.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 38 |
+
"layers.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 39 |
+
"layers.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 40 |
+
"layers.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 41 |
+
"layers.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 42 |
+
"layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 43 |
+
"layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 44 |
+
"layers.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 45 |
+
"layers.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 46 |
+
"layers.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 47 |
+
"layers.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 48 |
+
"layers.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 49 |
+
"layers.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 50 |
+
"layers.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 51 |
+
"layers.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 52 |
+
"layers.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 53 |
+
"layers.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 54 |
+
"layers.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 55 |
+
"layers.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 56 |
+
"layers.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 57 |
+
"layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 58 |
+
"layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 59 |
+
"layers.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 60 |
+
"layers.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 61 |
+
"layers.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 62 |
+
"layers.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 63 |
+
"layers.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 64 |
+
"layers.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 65 |
+
"layers.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 66 |
+
"layers.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 67 |
+
"layers.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 68 |
+
"layers.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 69 |
+
"layers.10.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 70 |
+
"layers.10.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 71 |
+
"layers.10.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 72 |
+
"layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 73 |
+
"layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 74 |
+
"layers.10.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 75 |
+
"layers.10.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 76 |
+
"layers.10.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 77 |
+
"layers.10.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 78 |
+
"layers.11.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 79 |
+
"layers.11.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 80 |
+
"layers.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 81 |
+
"layers.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 82 |
+
"layers.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 83 |
+
"layers.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 84 |
+
"layers.11.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 85 |
+
"layers.11.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 86 |
+
"layers.11.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 87 |
+
"layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 88 |
+
"layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 89 |
+
"layers.11.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 90 |
+
"layers.11.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 91 |
+
"layers.11.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 92 |
+
"layers.11.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 93 |
+
"layers.12.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 94 |
+
"layers.12.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 95 |
+
"layers.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 96 |
+
"layers.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 97 |
+
"layers.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 98 |
+
"layers.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 99 |
+
"layers.12.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 100 |
+
"layers.12.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 101 |
+
"layers.12.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 102 |
+
"layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 103 |
+
"layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 104 |
+
"layers.12.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 105 |
+
"layers.12.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 106 |
+
"layers.12.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 107 |
+
"layers.12.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 108 |
+
"layers.13.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 109 |
+
"layers.13.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 110 |
+
"layers.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 111 |
+
"layers.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 112 |
+
"layers.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 113 |
+
"layers.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 114 |
+
"layers.13.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 115 |
+
"layers.13.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 116 |
+
"layers.13.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 117 |
+
"layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 118 |
+
"layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 119 |
+
"layers.13.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 120 |
+
"layers.13.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 121 |
+
"layers.13.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 122 |
+
"layers.13.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 123 |
+
"layers.14.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 124 |
+
"layers.14.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 125 |
+
"layers.14.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 126 |
+
"layers.14.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 127 |
+
"layers.14.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 128 |
+
"layers.14.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 129 |
+
"layers.14.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 130 |
+
"layers.14.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 131 |
+
"layers.14.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 132 |
+
"layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 133 |
+
"layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 134 |
+
"layers.14.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 135 |
+
"layers.14.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 136 |
+
"layers.14.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 137 |
+
"layers.14.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 138 |
+
"layers.15.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 139 |
+
"layers.15.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 140 |
+
"layers.15.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 141 |
+
"layers.15.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 142 |
+
"layers.15.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 143 |
+
"layers.15.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 144 |
+
"layers.15.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 145 |
+
"layers.15.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 146 |
+
"layers.15.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 147 |
+
"layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 148 |
+
"layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 149 |
+
"layers.15.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 150 |
+
"layers.15.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 151 |
+
"layers.15.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 152 |
+
"layers.15.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 153 |
+
"layers.16.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 154 |
+
"layers.16.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 155 |
+
"layers.16.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 156 |
+
"layers.16.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 157 |
+
"layers.16.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 158 |
+
"layers.16.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 159 |
+
"layers.16.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 160 |
+
"layers.16.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 161 |
+
"layers.16.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 162 |
+
"layers.16.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 163 |
+
"layers.16.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 164 |
+
"layers.16.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 165 |
+
"layers.16.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 166 |
+
"layers.16.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 167 |
+
"layers.16.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 168 |
+
"layers.17.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 169 |
+
"layers.17.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 170 |
+
"layers.17.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 171 |
+
"layers.17.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 172 |
+
"layers.17.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 173 |
+
"layers.17.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 174 |
+
"layers.17.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 175 |
+
"layers.17.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 176 |
+
"layers.17.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 177 |
+
"layers.17.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 178 |
+
"layers.17.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 179 |
+
"layers.17.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 180 |
+
"layers.17.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 181 |
+
"layers.17.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 182 |
+
"layers.17.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 183 |
+
"layers.18.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 184 |
+
"layers.18.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 185 |
+
"layers.18.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 186 |
+
"layers.18.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 187 |
+
"layers.18.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 188 |
+
"layers.18.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 189 |
+
"layers.18.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 190 |
+
"layers.18.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 191 |
+
"layers.18.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 192 |
+
"layers.18.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 193 |
+
"layers.18.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 194 |
+
"layers.18.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 195 |
+
"layers.18.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 196 |
+
"layers.18.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 197 |
+
"layers.18.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 198 |
+
"layers.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 199 |
+
"layers.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 200 |
+
"layers.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 201 |
+
"layers.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 202 |
+
"layers.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 203 |
+
"layers.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 204 |
+
"layers.19.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 205 |
+
"layers.19.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 206 |
+
"layers.19.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 207 |
+
"layers.19.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 208 |
+
"layers.19.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 209 |
+
"layers.19.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 210 |
+
"layers.19.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 211 |
+
"layers.19.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 212 |
+
"layers.19.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 213 |
+
"layers.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 214 |
+
"layers.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 215 |
+
"layers.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 216 |
+
"layers.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 217 |
+
"layers.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 218 |
+
"layers.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 219 |
+
"layers.2.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 220 |
+
"layers.2.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 221 |
+
"layers.2.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 222 |
+
"layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 223 |
+
"layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 224 |
+
"layers.2.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 225 |
+
"layers.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 226 |
+
"layers.2.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 227 |
+
"layers.2.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 228 |
+
"layers.20.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 229 |
+
"layers.20.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 230 |
+
"layers.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 231 |
+
"layers.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 232 |
+
"layers.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 233 |
+
"layers.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 234 |
+
"layers.20.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 235 |
+
"layers.20.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 236 |
+
"layers.20.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 237 |
+
"layers.20.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 238 |
+
"layers.20.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 239 |
+
"layers.20.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 240 |
+
"layers.20.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 241 |
+
"layers.20.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 242 |
+
"layers.20.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 243 |
+
"layers.21.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 244 |
+
"layers.21.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 245 |
+
"layers.21.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 246 |
+
"layers.21.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 247 |
+
"layers.21.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 248 |
+
"layers.21.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 249 |
+
"layers.21.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 250 |
+
"layers.21.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 251 |
+
"layers.21.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 252 |
+
"layers.21.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 253 |
+
"layers.21.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 254 |
+
"layers.21.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 255 |
+
"layers.21.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 256 |
+
"layers.21.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 257 |
+
"layers.21.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 258 |
+
"layers.22.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 259 |
+
"layers.22.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 260 |
+
"layers.22.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 261 |
+
"layers.22.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 262 |
+
"layers.22.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 263 |
+
"layers.22.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 264 |
+
"layers.22.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 265 |
+
"layers.22.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 266 |
+
"layers.22.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 267 |
+
"layers.22.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 268 |
+
"layers.22.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 269 |
+
"layers.22.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 270 |
+
"layers.22.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 271 |
+
"layers.22.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 272 |
+
"layers.22.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 273 |
+
"layers.23.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 274 |
+
"layers.23.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 275 |
+
"layers.23.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 276 |
+
"layers.23.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 277 |
+
"layers.23.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 278 |
+
"layers.23.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 279 |
+
"layers.23.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 280 |
+
"layers.23.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 281 |
+
"layers.23.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 282 |
+
"layers.23.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 283 |
+
"layers.23.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 284 |
+
"layers.23.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 285 |
+
"layers.23.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 286 |
+
"layers.23.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 287 |
+
"layers.23.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 288 |
+
"layers.24.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 289 |
+
"layers.24.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 290 |
+
"layers.24.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 291 |
+
"layers.24.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 292 |
+
"layers.24.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 293 |
+
"layers.24.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 294 |
+
"layers.24.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 295 |
+
"layers.24.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 296 |
+
"layers.24.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 297 |
+
"layers.24.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 298 |
+
"layers.24.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 299 |
+
"layers.24.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 300 |
+
"layers.24.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 301 |
+
"layers.24.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 302 |
+
"layers.24.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 303 |
+
"layers.25.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 304 |
+
"layers.25.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 305 |
+
"layers.25.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 306 |
+
"layers.25.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 307 |
+
"layers.25.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 308 |
+
"layers.25.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 309 |
+
"layers.25.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 310 |
+
"layers.25.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 311 |
+
"layers.25.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 312 |
+
"layers.25.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 313 |
+
"layers.25.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 314 |
+
"layers.25.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 315 |
+
"layers.25.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 316 |
+
"layers.25.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 317 |
+
"layers.25.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 318 |
+
"layers.26.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 319 |
+
"layers.26.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 320 |
+
"layers.26.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 321 |
+
"layers.26.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 322 |
+
"layers.26.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 323 |
+
"layers.26.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 324 |
+
"layers.26.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 325 |
+
"layers.26.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 326 |
+
"layers.26.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 327 |
+
"layers.26.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 328 |
+
"layers.26.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 329 |
+
"layers.26.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 330 |
+
"layers.26.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 331 |
+
"layers.26.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 332 |
+
"layers.26.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 333 |
+
"layers.27.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 334 |
+
"layers.27.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 335 |
+
"layers.27.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 336 |
+
"layers.27.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 337 |
+
"layers.27.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 338 |
+
"layers.27.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 339 |
+
"layers.27.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 340 |
+
"layers.27.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 341 |
+
"layers.27.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 342 |
+
"layers.27.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 343 |
+
"layers.27.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 344 |
+
"layers.27.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 345 |
+
"layers.27.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 346 |
+
"layers.27.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 347 |
+
"layers.27.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 348 |
+
"layers.28.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 349 |
+
"layers.28.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 350 |
+
"layers.28.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 351 |
+
"layers.28.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 352 |
+
"layers.28.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 353 |
+
"layers.28.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 354 |
+
"layers.28.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 355 |
+
"layers.28.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 356 |
+
"layers.28.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 357 |
+
"layers.28.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 358 |
+
"layers.28.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 359 |
+
"layers.28.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 360 |
+
"layers.28.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 361 |
+
"layers.28.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 362 |
+
"layers.28.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 363 |
+
"layers.29.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 364 |
+
"layers.29.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 365 |
+
"layers.29.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 366 |
+
"layers.29.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 367 |
+
"layers.29.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 368 |
+
"layers.29.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 369 |
+
"layers.29.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 370 |
+
"layers.29.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 371 |
+
"layers.29.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 372 |
+
"layers.29.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 373 |
+
"layers.29.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 374 |
+
"layers.29.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 375 |
+
"layers.29.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 376 |
+
"layers.29.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 377 |
+
"layers.29.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 378 |
+
"layers.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 379 |
+
"layers.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 380 |
+
"layers.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 381 |
+
"layers.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 382 |
+
"layers.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 383 |
+
"layers.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 384 |
+
"layers.3.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 385 |
+
"layers.3.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 386 |
+
"layers.3.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 387 |
+
"layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 388 |
+
"layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 389 |
+
"layers.3.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 390 |
+
"layers.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 391 |
+
"layers.3.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 392 |
+
"layers.3.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 393 |
+
"layers.30.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 394 |
+
"layers.30.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 395 |
+
"layers.30.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 396 |
+
"layers.30.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 397 |
+
"layers.30.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 398 |
+
"layers.30.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 399 |
+
"layers.30.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 400 |
+
"layers.30.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 401 |
+
"layers.30.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 402 |
+
"layers.30.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 403 |
+
"layers.30.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 404 |
+
"layers.30.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 405 |
+
"layers.30.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 406 |
+
"layers.30.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 407 |
+
"layers.30.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 408 |
+
"layers.31.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 409 |
+
"layers.31.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 410 |
+
"layers.31.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 411 |
+
"layers.31.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 412 |
+
"layers.31.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 413 |
+
"layers.31.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 414 |
+
"layers.31.feed_forward.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 415 |
+
"layers.31.feed_forward.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 416 |
+
"layers.31.feed_forward.linear_3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 417 |
+
"layers.31.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 418 |
+
"layers.31.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 419 |
+
"layers.31.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 420 |
+
"layers.31.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 421 |
+
"layers.31.norm1.norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 422 |
+
"layers.31.norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 423 |
+
"layers.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 424 |
+
"layers.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 425 |
+
"layers.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 426 |
+
"layers.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 427 |
+
"layers.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 428 |
+
"layers.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 429 |
+
"layers.4.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 430 |
+
"layers.4.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 431 |
+
"layers.4.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 432 |
+
"layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 433 |
+
"layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 434 |
+
"layers.4.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 435 |
+
"layers.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 436 |
+
"layers.4.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 437 |
+
"layers.4.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 438 |
+
"layers.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 439 |
+
"layers.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 440 |
+
"layers.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 441 |
+
"layers.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 442 |
+
"layers.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 443 |
+
"layers.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 444 |
+
"layers.5.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 445 |
+
"layers.5.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 446 |
+
"layers.5.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 447 |
+
"layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 448 |
+
"layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 449 |
+
"layers.5.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 450 |
+
"layers.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 451 |
+
"layers.5.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 452 |
+
"layers.5.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 453 |
+
"layers.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 454 |
+
"layers.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 455 |
+
"layers.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 456 |
+
"layers.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 457 |
+
"layers.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 458 |
+
"layers.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 459 |
+
"layers.6.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 460 |
+
"layers.6.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 461 |
+
"layers.6.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 462 |
+
"layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 463 |
+
"layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 464 |
+
"layers.6.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 465 |
+
"layers.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 466 |
+
"layers.6.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 467 |
+
"layers.6.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 468 |
+
"layers.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 469 |
+
"layers.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 470 |
+
"layers.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 471 |
+
"layers.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 472 |
+
"layers.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 473 |
+
"layers.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 474 |
+
"layers.7.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 475 |
+
"layers.7.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 476 |
+
"layers.7.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 477 |
+
"layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 478 |
+
"layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 479 |
+
"layers.7.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 480 |
+
"layers.7.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 481 |
+
"layers.7.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 482 |
+
"layers.7.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 483 |
+
"layers.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 484 |
+
"layers.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 485 |
+
"layers.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 486 |
+
"layers.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 487 |
+
"layers.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 488 |
+
"layers.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 489 |
+
"layers.8.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 490 |
+
"layers.8.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 491 |
+
"layers.8.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 492 |
+
"layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 493 |
+
"layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 494 |
+
"layers.8.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 495 |
+
"layers.8.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 496 |
+
"layers.8.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 497 |
+
"layers.8.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 498 |
+
"layers.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 499 |
+
"layers.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 500 |
+
"layers.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 501 |
+
"layers.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 502 |
+
"layers.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 503 |
+
"layers.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 504 |
+
"layers.9.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 505 |
+
"layers.9.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 506 |
+
"layers.9.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 507 |
+
"layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 508 |
+
"layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 509 |
+
"layers.9.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 510 |
+
"layers.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 511 |
+
"layers.9.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 512 |
+
"layers.9.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 513 |
+
"noise_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 514 |
+
"noise_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 515 |
+
"noise_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 516 |
+
"noise_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 517 |
+
"noise_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 518 |
+
"noise_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 519 |
+
"noise_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 520 |
+
"noise_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 521 |
+
"noise_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 522 |
+
"noise_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 523 |
+
"noise_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 524 |
+
"noise_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 525 |
+
"noise_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 526 |
+
"noise_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 527 |
+
"noise_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 528 |
+
"noise_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 529 |
+
"noise_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 530 |
+
"noise_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 531 |
+
"noise_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 532 |
+
"noise_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 533 |
+
"noise_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 534 |
+
"noise_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 535 |
+
"noise_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 536 |
+
"noise_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 537 |
+
"noise_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 538 |
+
"noise_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 539 |
+
"noise_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 540 |
+
"noise_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 541 |
+
"noise_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 542 |
+
"noise_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 543 |
+
"norm_out.linear_1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 544 |
+
"norm_out.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 545 |
+
"norm_out.linear_2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 546 |
+
"norm_out.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 547 |
+
"ref_image_patch_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 548 |
+
"ref_image_patch_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 549 |
+
"ref_image_refiner.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 550 |
+
"ref_image_refiner.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 551 |
+
"ref_image_refiner.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 552 |
+
"ref_image_refiner.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 553 |
+
"ref_image_refiner.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 554 |
+
"ref_image_refiner.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 555 |
+
"ref_image_refiner.0.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 556 |
+
"ref_image_refiner.0.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 557 |
+
"ref_image_refiner.0.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 558 |
+
"ref_image_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 559 |
+
"ref_image_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 560 |
+
"ref_image_refiner.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 561 |
+
"ref_image_refiner.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 562 |
+
"ref_image_refiner.0.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 563 |
+
"ref_image_refiner.0.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 564 |
+
"ref_image_refiner.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 565 |
+
"ref_image_refiner.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 566 |
+
"ref_image_refiner.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 567 |
+
"ref_image_refiner.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 568 |
+
"ref_image_refiner.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 569 |
+
"ref_image_refiner.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 570 |
+
"ref_image_refiner.1.feed_forward.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 571 |
+
"ref_image_refiner.1.feed_forward.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 572 |
+
"ref_image_refiner.1.feed_forward.linear_3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 573 |
+
"ref_image_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 574 |
+
"ref_image_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 575 |
+
"ref_image_refiner.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 576 |
+
"ref_image_refiner.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 577 |
+
"ref_image_refiner.1.norm1.norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 578 |
+
"ref_image_refiner.1.norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 579 |
+
"time_caption_embed.caption_embedder.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 580 |
+
"time_caption_embed.caption_embedder.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 581 |
+
"time_caption_embed.caption_embedder.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 582 |
+
"time_caption_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 583 |
+
"time_caption_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 584 |
+
"time_caption_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 585 |
+
"time_caption_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 586 |
+
"x_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 587 |
+
"x_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
|
| 588 |
+
}
|
| 589 |
+
}
|
transformer/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "OmniGen2Transformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.35.1",
|
| 4 |
+
"axes_dim_rope": [
|
| 5 |
+
40,
|
| 6 |
+
40,
|
| 7 |
+
40
|
| 8 |
+
],
|
| 9 |
+
"axes_lens": [
|
| 10 |
+
10000,
|
| 11 |
+
10000,
|
| 12 |
+
10000
|
| 13 |
+
],
|
| 14 |
+
"ffn_dim_multiplier": null,
|
| 15 |
+
"hidden_size": 2520,
|
| 16 |
+
"in_channels": 16,
|
| 17 |
+
"max_ref_images": 10,
|
| 18 |
+
"multiple_of": 256,
|
| 19 |
+
"norm_eps": 1e-05,
|
| 20 |
+
"num_attention_heads": 21,
|
| 21 |
+
"num_kv_heads": 7,
|
| 22 |
+
"num_layers": 32,
|
| 23 |
+
"num_refiner_layers": 2,
|
| 24 |
+
"out_channels": null,
|
| 25 |
+
"patch_size": 2,
|
| 26 |
+
"text_feat_dim": 2048,
|
| 27 |
+
"timestep_scale": 1000.0
|
| 28 |
+
}
|
transformer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa1206f502268c6be56b0958eadc94027fd5dff78a29d33d18a581db3bd45319
|
| 3 |
+
size 7934409984
|
vae/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.33.1",
|
| 4 |
+
"_name_or_path": "/share_2/luoxin/modelscope/hub/models/FLUX.1-dev",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
128,
|
| 8 |
+
256,
|
| 9 |
+
512,
|
| 10 |
+
512
|
| 11 |
+
],
|
| 12 |
+
"down_block_types": [
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D",
|
| 16 |
+
"DownEncoderBlock2D"
|
| 17 |
+
],
|
| 18 |
+
"force_upcast": true,
|
| 19 |
+
"in_channels": 3,
|
| 20 |
+
"latent_channels": 16,
|
| 21 |
+
"latents_mean": null,
|
| 22 |
+
"latents_std": null,
|
| 23 |
+
"layers_per_block": 2,
|
| 24 |
+
"mid_block_add_attention": true,
|
| 25 |
+
"norm_num_groups": 32,
|
| 26 |
+
"out_channels": 3,
|
| 27 |
+
"sample_size": 1024,
|
| 28 |
+
"scaling_factor": 0.3611,
|
| 29 |
+
"shift_factor": 0.1159,
|
| 30 |
+
"up_block_types": [
|
| 31 |
+
"UpDecoderBlock2D",
|
| 32 |
+
"UpDecoderBlock2D",
|
| 33 |
+
"UpDecoderBlock2D",
|
| 34 |
+
"UpDecoderBlock2D"
|
| 35 |
+
],
|
| 36 |
+
"use_post_quant_conv": false,
|
| 37 |
+
"use_quant_conv": false
|
| 38 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94
|
| 3 |
+
size 335306212
|