Duplicate from microsoft/Mage-Flow
Browse filesCo-authored-by: Xinjie <Xinjie-Q@users.noreply.huggingface.co>
- .gitattributes +55 -0
- README.md +383 -0
- assets/cuisine.jpg +3 -0
- assets/dog.jpg +3 -0
- assets/edit_gallery_appearance.jpg +3 -0
- assets/edit_gallery_content.jpg +3 -0
- assets/edit_gallery_human_creative.jpg +3 -0
- assets/edit_gallery_lowlevel.jpg +3 -0
- assets/edit_gallery_restoration.jpg +3 -0
- assets/edit_gallery_scene_subject.jpg +3 -0
- assets/edit_gallery_showcase_1.jpg +3 -0
- assets/edit_gallery_showcase_2.jpg +3 -0
- assets/general.jpg +3 -0
- assets/mage-flow-cover.png +3 -0
- assets/mage_vae.jpg +3 -0
- assets/multiref_000000_0.jpg +0 -0
- assets/multiref_000000_1.png +3 -0
- assets/nr_mmdit.jpg +3 -0
- assets/one_to_many_editing_diversity.jpg +3 -0
- assets/portrait.jpg +3 -0
- assets/t2i_teaser.jpg +3 -0
- assets/text_en.jpg +3 -0
- assets/text_zh.jpg +3 -0
- model_index.json +26 -0
- scheduler/scheduler_config.json +7 -0
- text_encoder/.gitattributes +35 -0
- text_encoder/README.md +192 -0
- text_encoder/chat_template.json +4 -0
- text_encoder/config.json +63 -0
- text_encoder/generation_config.json +14 -0
- text_encoder/merges.txt +0 -0
- text_encoder/model-00001-of-00002.safetensors +3 -0
- text_encoder/model-00002-of-00002.safetensors +3 -0
- text_encoder/model.safetensors.index.json +720 -0
- text_encoder/preprocessor_config.json +21 -0
- text_encoder/tokenizer.json +0 -0
- text_encoder/tokenizer_config.json +239 -0
- text_encoder/video_preprocessor_config.json +21 -0
- text_encoder/vocab.json +0 -0
- transformer/config.json +34 -0
- transformer/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +6 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/cuisine.jpg filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
assets/dog.jpg filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
assets/edit_gallery_appearance.jpg filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
assets/edit_gallery_content.jpg filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
assets/edit_gallery_human_creative.jpg filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
assets/edit_gallery_lowlevel.jpg filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
assets/edit_gallery_restoration.jpg filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
assets/edit_gallery_scene_subject.jpg filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
assets/edit_gallery_showcase_1.jpg filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
assets/edit_gallery_showcase_2.jpg filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
assets/general.jpg filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
assets/mage-flow-cover.png filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
assets/mage_vae.jpg filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
assets/multiref_000000_1.png filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
assets/nr_mmdit.jpg filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
assets/one_to_many_editing_diversity.jpg filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
assets/portrait.jpg filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
assets/t2i_teaser.jpg filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
assets/text_en.jpg filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
assets/text_zh.jpg filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
pipeline_tag: text-to-image
|
| 5 |
+
tags:
|
| 6 |
+
- text-to-image
|
| 7 |
+
- image-generation
|
| 8 |
+
- image-editing
|
| 9 |
+
- diffusion
|
| 10 |
+
- rectified-flow
|
| 11 |
+
- mage-flow
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<h1 align="center">Mage-Flow<br><span style="font-size: 0.55em; font-weight: normal;">An Efficient Native-Resolution Foundation Model for Image Generation and Editing</span></h1>
|
| 15 |
+
|
| 16 |
+
<p align="center">
|
| 17 |
+
<a href="https://arxiv.org/abs/2607.19064"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-Mage--Flow-b31b1b" height="22" /></a>
|
| 18 |
+
<a href="https://microsoft.github.io/Mage"><img alt="Project Page" src="https://img.shields.io/badge/%F0%9F%8C%90-Project%20Page-blue" height="22" /></a>
|
| 19 |
+
<a href="https://github.com/microsoft/Mage"><img src="https://img.shields.io/badge/Code-GitHub-181717?logo=github" alt="GitHub"></a>
|
| 20 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Base"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Base-yellow" height="22" /></a>
|
| 21 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow-yellow" height="22" /></a>
|
| 22 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Turbo"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Turbo-yellow" height="22" /></a>
|
| 23 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Edit-Base"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Edit--Base-yellow" height="22" /></a>
|
| 24 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Edit"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Edit-yellow" height="22" /></a>
|
| 25 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Edit-Turbo"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Edit--Turbo-yellow" height="22" /></a>
|
| 26 |
+
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-green" alt="License: MIT"></a>
|
| 27 |
+
</p>
|
| 28 |
+
|
| 29 |
+
<!-- <p align="center">
|
| 30 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Base"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Base-yellow" height="22" /></a>
|
| 31 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow-yellow" height="22" /></a>
|
| 32 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Turbo"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Turbo-yellow" height="22" /></a>
|
| 33 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Edit-Base"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Edit--Base-yellow" height="22" /></a>
|
| 34 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Edit"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Edit-yellow" height="22" /></a>
|
| 35 |
+
<a href="https://huggingface.co/microsoft/Mage-Flow-Edit-Turbo"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Edit--Turbo-yellow" height="22" /></a>
|
| 36 |
+
</p> -->
|
| 37 |
+
|
| 38 |
+
<div align="center">
|
| 39 |
+
<img src="assets/mage-flow-cover.png" width="100%" alt="gallery">
|
| 40 |
+
</div>
|
| 41 |
+
|
| 42 |
+
---
|
| 43 |
+
|
| 44 |
+
**Mage-Flow** is a compact **4B-scale generative stack** for efficient **text-to-image generation** and **instruction-based image editing**. Instead of scaling to tens of billions of parameters, Mage-Flow reaches state-of-the-art-competitive quality through careful **tokenizer–backbone–system co-design**, so it stays fast, memory-light, and easy to fine-tune under realistic compute budgets.
|
| 45 |
+
|
| 46 |
+
The stack is built from **two shared, co-designed components**:
|
| 47 |
+
|
| 48 |
+
- **Mage-VAE** — a lightweight, high-fidelity latent tokenizer (one-step diffusion encode/decode with anchor-latent KL regularization).
|
| 49 |
+
- **NR-MMDiT** — a shared 4B **Native-Resolution Multimodal Diffusion Transformer**, trained with rectified flow matching in the Mage-VAE latent space.
|
| 50 |
+
|
| 51 |
+
Together with native-resolution packing and a fused-kernel training infrastructure, this shared stack powers **two model instantiations**: **Mage-Flow** for text-to-image generation and **Mage-Flow-Edit** for instruction-based image editing. Each ships in **Base**, **RL-aligned**, and **4-step Turbo** variants.
|
| 52 |
+
|
| 53 |
+
## ✨ Highlights
|
| 54 |
+
|
| 55 |
+
- **Compact & competitive.** A single 4B family for generation *and* editing that matches or beats much larger open systems (Qwen-Image 20B, Z-Image 6B, FLUX.2 32B, FireRed-Image-Edit 20B).
|
| 56 |
+
- **Efficient tokenizer.** Mage-VAE matches FLUX.2-VAE reconstruction fidelity while using **~12× / ~22× fewer encode / decode MACs per pixel**, removing the VAE as the high-resolution bottleneck.
|
| 57 |
+
- **Native resolution.** One checkpoint generates from **512 to 2048** on any aspect ratio, including extreme **4:1** (e.g. `512×2048`, `2048×512`).
|
| 58 |
+
- **System-level speed.** Native-resolution packing (FlashAttention var-len + per-sample 2D RoPE) + fused CUDA kernels raise MFU from **~33% → ~77%** (**~2.5× faster training**); CFG's conditional/unconditional branches run in **one** packed forward.
|
| 59 |
+
- **Full family.** **Base**, **RL-aligned**, and **4-step Turbo** variants for both generation and editing.
|
| 60 |
+
- **Versatile editing.** Mage-Flow-Edit supports semantic content editing, appearance transformation, image restoration, and structure-aware outputs within a unified image-and-text-conditioned model. See the report's editing galleries.
|
| 61 |
+
- **Interactive latency.** At `1024²` on a single A100: **Mage-Flow-Turbo 0.59 s/image**, **Mage-Flow-Edit-Turbo 1.02 s/edit**, peak memory **~18–20 GB** (lowest among compared systems).
|
| 62 |
+
|
| 63 |
+
<div align="center">
|
| 64 |
+
<img src="assets/one_to_many_editing_diversity.jpg" width="100%" alt="One-to-many editing diversity"><br>
|
| 65 |
+
<em>One-to-many editing diversity — Mage-Flow-Edit can generate diverse outputs from a single reference image.</em>
|
| 66 |
+
</div>
|
| 67 |
+
|
| 68 |
+
## 📥 Model Zoo
|
| 69 |
+
|
| 70 |
+
Each checkpoint is a self-contained diffusers-style repo (`transformer/` + shared `vae/`, `text_encoder/`, `scheduler/`).
|
| 71 |
+
|
| 72 |
+
| Model | Task | Variant | Steps | Hugging Face |
|
| 73 |
+
| :-------------------------- | :---------- | :----------------- | :---: | :---------------------------------------------------------------------------------------- |
|
| 74 |
+
| `Mage-Flow-4B-Base` | text→image | Base | 30 | [🤗 microsoft/Mage-Flow-Base](https://huggingface.co/microsoft/Mage-Flow-Base) |
|
| 75 |
+
| `Mage-Flow-4B` | text→image | RL-aligned | 20 | [🤗 microsoft/Mage-Flow](https://huggingface.co/microsoft/Mage-Flow) |
|
| 76 |
+
| `Mage-Flow-4B-Turbo` | text→image | Few-step distilled | 4 | [🤗 microsoft/Mage-Flow-Turbo](https://huggingface.co/microsoft/Mage-Flow-Turbo) |
|
| 77 |
+
| `Mage-Flow-Edit-4B-Base` | editing | Base | 30 | [🤗 microsoft/Mage-Flow-Edit-Base](https://huggingface.co/microsoft/Mage-Flow-Edit-Base) |
|
| 78 |
+
| `Mage-Flow-Edit-4B` | editing | RL-aligned | 30 | [🤗 microsoft/Mage-Flow-Edit](https://huggingface.co/microsoft/Mage-Flow-Edit) |
|
| 79 |
+
| `Mage-Flow-Edit-4B-Turbo` | editing | Few-step distilled | 4 | [🤗 microsoft/Mage-Flow-Edit-Turbo](https://huggingface.co/microsoft/Mage-Flow-Edit-Turbo) |
|
| 80 |
+
|
| 81 |
+
## 🖼️ Showcase
|
| 82 |
+
|
| 83 |
+
**Text-to-image** — prompt following, fine detail, and legible English/Chinese text rendering. *(The first panel is open; click a title to expand the others.)*
|
| 84 |
+
|
| 85 |
+
<details open>
|
| 86 |
+
<summary><b>Showcase</b></summary>
|
| 87 |
+
<div align="center"><img src="assets/t2i_teaser.jpg" width="100%" alt="t2i teaser"></div>
|
| 88 |
+
</details>
|
| 89 |
+
|
| 90 |
+
<details>
|
| 91 |
+
<summary><b>General scenes</b></summary>
|
| 92 |
+
<div align="center"><img src="assets/general.jpg" width="100%" alt="general scenes"></div>
|
| 93 |
+
</details>
|
| 94 |
+
|
| 95 |
+
<details>
|
| 96 |
+
<summary><b>Portraits</b></summary>
|
| 97 |
+
<div align="center"><img src="assets/portrait.jpg" width="100%" alt="portraits"></div>
|
| 98 |
+
</details>
|
| 99 |
+
|
| 100 |
+
<details>
|
| 101 |
+
<summary><b>Cuisine & still life</b></summary>
|
| 102 |
+
<div align="center"><img src="assets/cuisine.jpg" width="100%" alt="cuisine"></div>
|
| 103 |
+
</details>
|
| 104 |
+
|
| 105 |
+
<details>
|
| 106 |
+
<summary><b>English text rendering</b></summary>
|
| 107 |
+
<div align="center"><img src="assets/text_en.jpg" width="100%" alt="english text"></div>
|
| 108 |
+
</details>
|
| 109 |
+
|
| 110 |
+
<details>
|
| 111 |
+
<summary><b>Chinese text rendering</b></summary>
|
| 112 |
+
<div align="center"><img src="assets/text_zh.jpg" width="100%" alt="chinese text"></div>
|
| 113 |
+
</details>
|
| 114 |
+
|
| 115 |
+
**Instruction-based editing** — appearance, content, scene/subject, human-centered & creative, low-level, and restoration edits (source → result). *(The first panel is open; click a title to expand the others.)*
|
| 116 |
+
|
| 117 |
+
<details open>
|
| 118 |
+
<summary><b>Various Editing I</b></summary>
|
| 119 |
+
<div align="center"><img src="assets/edit_gallery_showcase_1.jpg" width="100%" alt="editing showcase 1"></div>
|
| 120 |
+
</details>
|
| 121 |
+
|
| 122 |
+
<details>
|
| 123 |
+
<summary><b>Various Editing II</b></summary>
|
| 124 |
+
<div align="center"><img src="assets/edit_gallery_showcase_2.jpg" width="100%" alt="editing showcase 2"></div>
|
| 125 |
+
</details>
|
| 126 |
+
|
| 127 |
+
<details>
|
| 128 |
+
<summary><b>Localized content & object editing</b></summary>
|
| 129 |
+
<div align="center"><img src="assets/edit_gallery_content.jpg" width="100%" alt="content editing"></div>
|
| 130 |
+
</details>
|
| 131 |
+
|
| 132 |
+
<details>
|
| 133 |
+
<summary><b>Scene, subject & camera transformations</b></summary>
|
| 134 |
+
<div align="center"><img src="assets/edit_gallery_scene_subject.jpg" width="100%" alt="scene and subject"></div>
|
| 135 |
+
</details>
|
| 136 |
+
|
| 137 |
+
<details>
|
| 138 |
+
<summary><b>Appearance & artistic rendering</b></summary>
|
| 139 |
+
<div align="center"><img src="assets/edit_gallery_appearance.jpg" width="100%" alt="appearance"></div>
|
| 140 |
+
</details>
|
| 141 |
+
|
| 142 |
+
<details>
|
| 143 |
+
<summary><b>Human-centered & creative editing</b></summary>
|
| 144 |
+
<div align="center"><img src="assets/edit_gallery_human_creative.jpg" width="100%" alt="human-centered and creative"></div>
|
| 145 |
+
</details>
|
| 146 |
+
|
| 147 |
+
<details>
|
| 148 |
+
<summary><b>Low-level vision & conditional reconstruction</b></summary>
|
| 149 |
+
<div align="center"><img src="assets/edit_gallery_lowlevel.jpg" width="100%" alt="low-level vision"></div>
|
| 150 |
+
</details>
|
| 151 |
+
|
| 152 |
+
<details>
|
| 153 |
+
<summary><b>Bidirectional degradation & restoration</b></summary>
|
| 154 |
+
<div align="center"><img src="assets/edit_gallery_restoration.jpg" width="100%" alt="restoration"></div>
|
| 155 |
+
</details>
|
| 156 |
+
|
| 157 |
+
## 📊 Performance
|
| 158 |
+
|
| 159 |
+
<details>
|
| 160 |
+
<summary><b>Full benchmark tables (text-to-image & image editing) — click to expand</b></summary>
|
| 161 |
+
|
| 162 |
+
**Text-to-image** — full benchmark suite: GenEval, DPG-Bench, TIIF-Bench (short/long splits), CVTG-2K, OneIG (EN/CN), LongText (EN/CN). Higher is better; GenEval / CVTG-2K / OneIG / LongText on a 0–1 scale, DPG / TIIF on 0–100. The **Type** column marks closed- vs open-source; **bold** / <ins>underline</ins> = best / second-best among **open-source** models (closed-source shown for reference, not ranked); `–` = not reported; ★ = ours.
|
| 163 |
+
|
| 164 |
+
| Model | Type | #Params | Steps | GenEval | DPG | TIIF-Short | TIIF-Long | CVTG-2K | OneIG-EN | OneIG-CN | LongText-EN | LongText-CN |
|
| 165 |
+
| :--------------------------- | :----: | :-----: | :---: | :-------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: |
|
| 166 |
+
| Seedream 3.0 | Closed | – | – | 0.84 | 88.27 | 86.02 | 84.31 | 0.592 | 0.530 | 0.528 | 0.896 | 0.878 |
|
| 167 |
+
| Seedream 4.0 | Closed | – | – | 0.84 | 88.63 | – | – | 0.892 | 0.573 | 0.554 | 0.936 | 0.946 |
|
| 168 |
+
| GPT-Image-1 | Closed | – | – | 0.84 | 85.15 | 89.15 | 88.29 | 0.857 | 0.533 | 0.474 | 0.956 | 0.619 |
|
| 169 |
+
| Nano-Banana-Pro | Closed | – | – | 0.83 | 87.16 | – | – | 0.779 | 0.580 | 0.570 | 0.981 | 0.949 |
|
| 170 |
+
| FLUX.1-dev | Open | 12B | 50 | 0.66 | 83.84 | 71.09 | 71.78 | 0.496 | 0.434 | 0.245 | 0.607 | 0.005 |
|
| 171 |
+
| FLUX.1-Krea-dev | Open | 12B | 50 | 0.72 | 86.59 | 80.36 | 81.67 | 0.444 | 0.443 | 0.271 | 0.693 | 0.002 |
|
| 172 |
+
| FLUX.2-dev | Open | 32B | 50 | 0.87 | 87.57 | **88.82** | **88.10** | **0.893** | **0.551** | 0.516 | **0.963** | 0.757 |
|
| 173 |
+
| FLUX.2-Klein-Base-4B | Open | 4B | 50 | 0.78 | 83.02 | 79.94 | 80.01 | 0.656 | 0.485 | 0.366 | 0.554 | 0.071 |
|
| 174 |
+
| FLUX.2-Klein-Base-9B | Open | 9B | 50 | 0.83 | 85.29 | 81.47 | 84.52 | 0.655 | 0.544 | 0.400 | 0.872 | 0.227 |
|
| 175 |
+
| FLUX.2-Klein-4B | Open | 4B | 4 | 0.83 | 85.53 | 78.91 | 79.04 | 0.628 | 0.500 | 0.364 | 0.649 | 0.068 |
|
| 176 |
+
| FLUX.2-Klein-9B | Open | 9B | 4 | 0.86 | 86.20 | 85.22 | 84.13 | 0.424 | 0.538 | 0.406 | 0.872 | 0.226 |
|
| 177 |
+
| Qwen-Image | Open | 20B | 50 | 0.87 | **88.32** | <ins>86.14</ins> | <ins>86.83</ins> | 0.829 | 0.539 | **0.548** | 0.943 | 0.946 |
|
| 178 |
+
| JoyAI-Image | Open | 16B | 50 | – | 88.05 | – | – | 0.874 | 0.542 | 0.521 | **0.963** | **0.963** |
|
| 179 |
+
| HunyuanImage-3.0 | Open | 80B | 50 | 0.72 | 86.10 | – | – | 0.765 | – | – | – | – |
|
| 180 |
+
| LongCat-Image | Open | 6B | 50 | 0.87 | 86.80 | 80.93 | 81.30 | 0.866 | 0.516 | 0.518 | 0.885 | <ins>0.956</ins> |
|
| 181 |
+
| Z-Image-Base | Open | 6B | 50 | 0.84 | <ins>88.14</ins> | 80.20 | 83.04 | 0.867 | <ins>0.546</ins> | <ins>0.535</ins> | 0.935 | 0.936 |
|
| 182 |
+
| Z-Image-Turbo | Open | 6B | 8 | 0.82 | 84.86 | 77.73 | 80.05 | 0.859 | 0.528 | 0.507 | 0.917 | 0.926 |
|
| 183 |
+
| **Mage-Flow-Base** ★ | Open | 4B | 30 | 0.79 | 86.26 | 82.50 | 83.19 | 0.851 | 0.542 | 0.509 | 0.904 | 0.792 |
|
| 184 |
+
| **Mage-Flow** ★ | Open | 4B | 20 | **0.90** | 86.49 | 82.19 | 84.70 | <ins>0.887</ins> | 0.536 | 0.505 | <ins>0.944</ins> | 0.823 |
|
| 185 |
+
| **Mage-Flow-Turbo** ★ | Open | 4B | 4 | <ins>0.88</ins> | 85.48 | 83.58 | 84.16 | 0.873 | 0.523 | 0.491 | 0.911 | 0.801 |
|
| 186 |
+
|
| 187 |
+
**Image editing** — ImgEdit-Bench (0–5), GEdit-Bench EN/CN (0–10), TextEdit-Bench synthetic/real (0–25). Higher is better; the **Type** column marks closed- vs open-source; **bold** / <ins>underline</ins> = best / second-best among **open-source** models; `–` = not reported; ★ = ours.
|
| 188 |
+
|
| 189 |
+
| Model | Type | #Params | Steps | ImgEdit | GEdit-EN | GEdit-CN | TextEdit-Syn | TextEdit-Real |
|
| 190 |
+
| :-------------------------------- | :----: | :-----: | :---: | :-------------: | :--------------: | :--------------: | :--------------: | :--------------: |
|
| 191 |
+
| Nano-Banana | Closed | – | – | 4.29 | 7.291 | 7.399 | 16.54 | 18.22 |
|
| 192 |
+
| Seedream 4.0 | Closed | – | – | 4.30 | 7.701 | 7.692 | 14.90 | 18.54 |
|
| 193 |
+
| Seedream 4.5 | Closed | – | – | 4.32 | 7.820 | 7.800 | – | – |
|
| 194 |
+
| Nano-Banana-Pro | Closed | – | – | 4.37 | 7.738 | 7.799 | – | – |
|
| 195 |
+
| Step1X-Edit-v1.2 | Open | 19B | 50 | 3.95 | 7.480 | 7.467 | 9.26 | 12.02 |
|
| 196 |
+
| FLUX.1-Kontext-dev | Open | 12B | 28 | 3.71 | 6.462 | 1.857 | 12.14 | 14.31 |
|
| 197 |
+
| FLUX.2-dev | Open | 32B | 50 | 4.35 | 7.413 | 7.278 | 11.86 | 14.71 |
|
| 198 |
+
| FLUX.2-Klein-Base-4B | Open | 4B | 50 | 3.80 | 7.081 | 7.102 | 11.01 | 13.79 |
|
| 199 |
+
| FLUX.2-Klein-4B | Open | 4B | 4 | 4.01 | 7.717 | 7.750 | 11.84 | 14.46 |
|
| 200 |
+
| FLUX.2-Klein-Base-9B | Open | 9B | 50 | 4.05 | 7.740 | 7.745 | 12.76 | 15.65 |
|
| 201 |
+
| FLUX.2-Klein-9B | Open | 9B | 4 | 4.18 | 8.040 | 8.055 | 12.73 | 15.75 |
|
| 202 |
+
| Z-Image-Edit | Open | 6B | 50 | 4.30 | 7.570 | 7.540 | – | – |
|
| 203 |
+
| Qwen-Image-Edit-2509 | Open | 20B | 50 | 4.31 | 7.480 | 7.467 | 13.40 | 15.81 |
|
| 204 |
+
| Qwen-Image-Edit-2511 | Open | 20B | 50 | <ins>4.51</ins> | 7.877 | 7.819 | 13.53 | <ins>16.81</ins> |
|
| 205 |
+
| LongCat-Image-Edit | Open | 6B | 50 | 4.45 | 7.748 | 7.731 | 12.46 | 14.89 |
|
| 206 |
+
| FireRed-Image-Edit-1.0 | Open | 20B | 50 | **4.56** | 7.943 | 7.887 | **15.19** | **17.23** |
|
| 207 |
+
| JoyAI-Image-Edit | Open | 16B | 50 | 4.46 | **8.276** | <ins>8.125</ins> | <ins>14.80</ins> | **17.23** |
|
| 208 |
+
| **Mage-Flow-Edit-Base** ★ | Open | 4B | 30 | 4.28 | 7.860 | 7.970 | 13.63 | 15.57 |
|
| 209 |
+
| **Mage-Flow-Edit** ★ | Open | 4B | 30 | 4.34 | 8.127 | 8.123 | 14.14 | 16.26 |
|
| 210 |
+
| **Mage-Flow-Edit-Turbo** ★ | Open | 4B | 4 | 4.38 | <ins>8.271</ins> | **8.264** | 12.77 | 15.41 |
|
| 211 |
+
|
| 212 |
+
</details>
|
| 213 |
+
|
| 214 |
+
## 🏗️ Architecture
|
| 215 |
+
|
| 216 |
+
**Mage-VAE** — a latent tokenizer built as a *symmetric* one-step diffusion codec: the decoder is a fully-convolutional one-step pixel-diffusion model (no global-attention blocks), and the encoder is its architectural dual (a one-step latent generator conditioned on pixels). A standard Gaussian-prior KL is replaced with an **anchor-latent KL** that regularizes the posterior toward FLUX.2-VAE latents, giving a generation-ready `128`-channel, `16×`-downsampled latent space.
|
| 217 |
+
|
| 218 |
+
<div align="center">
|
| 219 |
+
<img src="assets/mage_vae.jpg" width="100%" alt="Mage-VAE architecture and training"><br>
|
| 220 |
+
<em>Mage-VAE — anchor VAE (FLUX.2-VAE), the symmetric one-step encoder/decoder architecture, and the three-stage training pipeline.</em>
|
| 221 |
+
</div>
|
| 222 |
+
|
| 223 |
+
**Mage-Flow** — a 4B Multimodal DiT that encodes prompts with **Qwen3-VL** and images with Mage-VAE, then processes **packed** variable-length image+text sequences with per-sample 2D rotary embeddings and joint self-attention. **Native-resolution packing** removes bucket quantization and padding, lets one checkpoint generalize to any output size, and fuses the CFG cond/uncond branches into a single forward.
|
| 224 |
+
|
| 225 |
+
<div align="center">
|
| 226 |
+
<img src="assets/nr_mmdit.jpg" width="100%" alt="Mage-Flow / Native-Resolution MMDiT architecture"><br>
|
| 227 |
+
<em>Mage-Flow — native-resolution packing of variable-length image+text tokens through the Native-Resolution MMDiT (left), and the dual-stream MMDiT block (right).</em>
|
| 228 |
+
</div>
|
| 229 |
+
|
| 230 |
+
**Post-training** — from `Base`, generation is aligned with **Diffusion-NFT** (prompt following, aesthetics, text rendering, preference) to produce the RL model, and distilled with **decoupled-DMD + adversarial perceptual guidance** into the 4-step `Turbo`. Editing models reuse the recipe, trained on a mixture of generation and editing data to keep the generative prior.
|
| 231 |
+
|
| 232 |
+
## 🚀 Quick Start
|
| 233 |
+
|
| 234 |
+
### Installation
|
| 235 |
+
|
| 236 |
+
Install everything **except** `flash-attn` first, then install `flash-attn` separately with build isolation **off** — it compiles a CUDA extension against your installed torch, so torch and a matching CUDA toolkit must already be present.
|
| 237 |
+
|
| 238 |
+
```bash
|
| 239 |
+
cd Mage/mage_flow
|
| 240 |
+
uv venv && source .venv/bin/activate
|
| 241 |
+
|
| 242 |
+
# 1) Pinned, tested dependency set (torch 2.13, transformers 5.5, diffusers 0.38, pillow 12.3, …).
|
| 243 |
+
# Recommended for reproducibility. `uv pip install -e .` also works, but its loose
|
| 244 |
+
# bounds may resolve to a newer torch/transformers than the code was tested against.
|
| 245 |
+
uv pip install -r requirements.txt
|
| 246 |
+
uv pip install -e . --no-deps # the mage-flow package itself
|
| 247 |
+
|
| 248 |
+
# 2) flash-attn — needs build tools present and a CUDA toolkit whose MAJOR version
|
| 249 |
+
# matches your torch build (e.g. torch cu12x ↔ nvcc 12.x). A cu13/nvcc-12 mix fails.
|
| 250 |
+
uv pip install setuptools wheel ninja
|
| 251 |
+
uv pip install --no-build-isolation flash-attn==2.8.3
|
| 252 |
+
```
|
| 253 |
+
|
| 254 |
+
Plain `pip` is equivalent (`pip install -r requirements.txt`, `pip install -e . --no-deps`, then the two flash-attn lines). This registers three commands: `mage-flow`, `mage-flow-edit`, `mage-flow-app`.
|
| 255 |
+
|
| 256 |
+
> **torch / CUDA:** the default PyPI torch wheel targets the newest CUDA (currently cu13x). If your machine's CUDA toolkit is 12.x, install torch from the matching index first, e.g. `uv pip install torch==2.13.0 torchvision==0.28.0 --index-url https://download.pytorch.org/whl/cu126`, otherwise the flash-attn build will fail with a CUDA-version mismatch. (torch 2.13.0 ships cu126/cu129/cu130 wheels — pick the one matching your `nvcc`.)
|
| 257 |
+
|
| 258 |
+
### Python API
|
| 259 |
+
|
| 260 |
+
`pipe.generate(prompts, **kw)` and `pipe.edit(prompts, ref_images, **kw)` return a `list[PIL.Image]` aligned with `prompts`. A `prompts` **list** is batched into one packed forward per denoise step (each sample can have its own resolution/seed).
|
| 261 |
+
|
| 262 |
+
**Text-to-image:**
|
| 263 |
+
|
| 264 |
+
```python
|
| 265 |
+
from mage_flow import MageFlowPipeline
|
| 266 |
+
|
| 267 |
+
pipe = MageFlowPipeline.from_pretrained("microsoft/Mage-Flow", device="cuda")
|
| 268 |
+
|
| 269 |
+
# 1) single image
|
| 270 |
+
img = pipe.generate(["A close-up portrait of an elderly African man with deep wrinkles, wearing a traditional hat, soft natural lighting, ultra realistic."],
|
| 271 |
+
steps=20, cfg=5.0, heights=[1024], widths=[1024])[0]
|
| 272 |
+
img.save("t2i.png")
|
| 273 |
+
|
| 274 |
+
# 2) batch: several prompts / resolutions / seeds in ONE packed forward per step
|
| 275 |
+
imgs = pipe.generate(
|
| 276 |
+
["the Salar de Uyuni mirror surface captured at high noon, with intimate stillness permeating the air. dew beads on every blade of grass. National Geographic editorial, cinematic depth, fine-grained natural texture.",
|
| 277 |
+
"A close-up portrait of an elderly African man with deep wrinkles, wearing a traditional hat, soft natural lighting, ultra realistic.",
|
| 278 |
+
"An immersive close-up of a steaming bowl of Sichuan mapo tofu over jasmine rice served on a hand-thrown ceramic plate, finished with a wedge of citrus. Surface oils catch a tiny specular highlight. Shot with a Hasselblad H6D-100c, ambient window light, the kind of image that makes the viewer hungry."],
|
| 279 |
+
heights=[512, 1024, 1792], widths=[2048, 1024, 1024], # per-sample; 4:1 is fine
|
| 280 |
+
seeds=[1, 2, 3], steps=20, cfg=5.0,
|
| 281 |
+
)
|
| 282 |
+
```
|
| 283 |
+
|
| 284 |
+
**Image editing:**
|
| 285 |
+
|
| 286 |
+
```python
|
| 287 |
+
from mage_flow import MageFlowPipeline
|
| 288 |
+
|
| 289 |
+
pipe = MageFlowPipeline.from_pretrained("microsoft/Mage-Flow-Edit", device="cuda")
|
| 290 |
+
|
| 291 |
+
# single reference (path or PIL image)
|
| 292 |
+
img = pipe.edit(["Replace the background with a field of sunflowers"], ["assets/dog.jpg"],
|
| 293 |
+
steps=30, cfg=5.0, max_size=1024)[0]
|
| 294 |
+
img.save("single_edit.png")
|
| 295 |
+
|
| 296 |
+
# multi-image edit — ref_images[i] is a LIST of source images
|
| 297 |
+
img = pipe.edit(["blend the object from image 2 into image 1"],
|
| 298 |
+
[["scene.png", "object.png"]], steps=30, cfg=5.0)[0]
|
| 299 |
+
img.save("multi_edit.png")
|
| 300 |
+
|
| 301 |
+
# explicit output size (overrides max_size); Turbo edit = 4 steps / cfg 1
|
| 302 |
+
img = pipe.edit(["Replace the background with a field of sunflowers"], ["assets/dog.jpg"],
|
| 303 |
+
heights=[1024], widths=[1024], steps=4, cfg=1.0)[0]
|
| 304 |
+
img.save("single_edit_1024x1024.png")
|
| 305 |
+
```
|
| 306 |
+
|
| 307 |
+
**Parameters** (shared by `generate` / `edit`):
|
| 308 |
+
|
| 309 |
+
| Parameter | Default | Description |
|
| 310 |
+
| :------------------------------- | :--------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
| 311 |
+
| `prompts` | — | string or list of strings; a list is batched into one forward per step |
|
| 312 |
+
| `ref_images` *(edit)* | — | per prompt: one image/path, or a**list** of images for multi-image edit |
|
| 313 |
+
| `steps` | `30` | denoising steps — Base`30`, RL `20`, Turbo `4` |
|
| 314 |
+
| `cfg` | `5.0` | classifier-free guidance scale (Turbo:`1.0`) |
|
| 315 |
+
| `heights`, `widths` | `[1024]` | per-sample output size, multiple of 16; native resolution`512`–`2048` |
|
| 316 |
+
| `max_size` *(edit)* | source size | longest output side; short side follows the reference's aspect ratio |
|
| 317 |
+
| `vl_cond_long_edge` *(edit)* | `384` | cap the long edge of the reference image fed to the**VL text encoder** (matches training preprocessing; the VAE/generation path keeps the full output resolution). `0`/`None` disables |
|
| 318 |
+
| `neg_prompts` | `" "` | per-sample negative prompt (applied when`cfg > 1`) |
|
| 319 |
+
| `seeds` | `42` | per-sample seed;`-1` = random |
|
| 320 |
+
| `batch_cfg` | `True` | fuse the CFG conditional + unconditional passes into one packed forward |
|
| 321 |
+
| `renormalization` | `False` | rescale guided velocity per token (reduces over-saturation at high cfg) |
|
| 322 |
+
| `static_shift` | `6.0` | override the flow-matching sigma shift |
|
| 323 |
+
| `prompt_template` | `mage-flow` / `mage-flow-edit` | text-encoder prompt template |
|
| 324 |
+
|
| 325 |
+
### CLI
|
| 326 |
+
|
| 327 |
+
```bash
|
| 328 |
+
# text-to-image (two prompts in one batch)
|
| 329 |
+
mage-flow --prompt "A close-up portrait of an elderly African man with deep wrinkles, wearing a traditional hat, soft natural lighting, ultra realistic." "An immersive landscape of a Greenlandic icefjord at midnight sun, painted by early dawn light, crystal-clear skies adding drama. fine grains of sand carving sharp shadows. Peter Lik gallery print, moody atmosphere, museum-grade composition." \
|
| 330 |
+
--model_path microsoft/Mage-Flow --steps 20 --cfg 5.0 \
|
| 331 |
+
--height 1024 512 --width 1024 2048 --seed 42 --out ./outputs
|
| 332 |
+
|
| 333 |
+
|
| 334 |
+
# editing (one --ref per prompt; comma-separate sources for multi-image edit)
|
| 335 |
+
mage-flow-edit --prompt "Replace the background with a field of sunflowers" "blend these two images" \
|
| 336 |
+
--ref assets/dog.jpg "scene.png,object.png" \
|
| 337 |
+
--model_path microsoft/Mage-Flow-Edit --max_size 1024 --out ./outputs
|
| 338 |
+
```
|
| 339 |
+
|
| 340 |
+
| Flag | Scope | Meaning |
|
| 341 |
+
| :-------------------- | :---: | :---------------------------------------------------------------------------- |
|
| 342 |
+
| `--prompt` | both | one or more prompts, run as a batch (sample `i` uses `--seed + i`) |
|
| 343 |
+
| `--model_path` | both | local repo dir or HF Hub repo id (auto-downloaded + cached) |
|
| 344 |
+
| `--steps` | both | number of denoising steps |
|
| 345 |
+
| `--cfg` | both | classifier-free guidance scale |
|
| 346 |
+
| `--height` | both | output height — one value, or one per prompt for mixed resolutions |
|
| 347 |
+
| `--width` | both | output width — one value, or one per prompt for mixed resolutions |
|
| 348 |
+
| `--seed` | both | base seed (sample `i` uses `--seed + i`) |
|
| 349 |
+
| `--neg_prompt` | both | negative prompt |
|
| 350 |
+
| `--static_shift` | both | override the flow-matching sigma shift |
|
| 351 |
+
| `--out` | both | output directory |
|
| 352 |
+
| `--ref` | edit | reference image per prompt (comma-separate paths for a multi-image edit) |
|
| 353 |
+
| `--max_size` | edit | max size of the reference image |
|
| 354 |
+
| `--vl_cond_long_edge` | edit | VL-condition long edge (default `384`) |
|
| 355 |
+
|
| 356 |
+
### Gradio app
|
| 357 |
+
|
| 358 |
+
```bash
|
| 359 |
+
mage-flow-app # serve on http://0.0.0.0:7860 (or: python -m mage_flow.app)
|
| 360 |
+
```
|
| 361 |
+
|
| 362 |
+
A web UI with **Text → Image** and **Image Edit** tabs; models load lazily on first use and are cached. Presets default to the `microsoft/Mage-Flow*` **Hugging Face repos** (downloaded + cached on first use); set `MAGEFLOW_HF_DIR` to load local checkpoint dirs instead.
|
| 363 |
+
|
| 364 |
+
**Launch options:**
|
| 365 |
+
|
| 366 |
+
| Flag | Default | Meaning |
|
| 367 |
+
| :------------ | :---------- | :-------------------------------------------------------------------------- |
|
| 368 |
+
| `--host` | `0.0.0.0` | bind address |
|
| 369 |
+
| `--port` | `7860` | port |
|
| 370 |
+
| `--device` | `cuda` | inference device |
|
| 371 |
+
| `--share` | off | create a public Gradio share link |
|
| 372 |
+
| `--preload` | *(lazy)* | comma-separated repo ids / paths to load at startup instead of on first use |
|
| 373 |
+
|
| 374 |
+
## 📝 Citation
|
| 375 |
+
|
| 376 |
+
```bibtex
|
| 377 |
+
@article{zhang2026mageflow,
|
| 378 |
+
title={Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing},
|
| 379 |
+
author={Zhang, Xinjie and Zhang, Peng and Zheng, Shicheng and Guo, Jinghao and Jia, Zhaoyang and Shen, Yifei and Guo, Xun and Luo, Yuxuan and Li, Jiahao and Xie, Wenxuan and Pu, Fanyi and Zhang, Xiaoyi and Zhang, Kaichen and Guo, Zongyu and Bi, Tianci and Gui, Dongnan and Liu, Zhening and Wen, Zimo and Zheng, Zihan and Yang, Senqiao and Li, Xiao and Wang, Jinglu and Li, Bin and Lu, Yan},
|
| 380 |
+
journal={arXiv preprint arXiv:2607.19064},
|
| 381 |
+
year={2026}
|
| 382 |
+
}
|
| 383 |
+
```
|
assets/cuisine.jpg
ADDED
|
Git LFS Details
|
assets/dog.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_appearance.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_content.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_human_creative.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_lowlevel.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_restoration.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_scene_subject.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_showcase_1.jpg
ADDED
|
Git LFS Details
|
assets/edit_gallery_showcase_2.jpg
ADDED
|
Git LFS Details
|
assets/general.jpg
ADDED
|
Git LFS Details
|
assets/mage-flow-cover.png
ADDED
|
Git LFS Details
|
assets/mage_vae.jpg
ADDED
|
Git LFS Details
|
assets/multiref_000000_0.jpg
ADDED
|
assets/multiref_000000_1.png
ADDED
|
Git LFS Details
|
assets/nr_mmdit.jpg
ADDED
|
Git LFS Details
|
assets/one_to_many_editing_diversity.jpg
ADDED
|
Git LFS Details
|
assets/portrait.jpg
ADDED
|
Git LFS Details
|
assets/t2i_teaser.jpg
ADDED
|
Git LFS Details
|
assets/text_en.jpg
ADDED
|
Git LFS Details
|
assets/text_zh.jpg
ADDED
|
Git LFS Details
|
model_index.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MageFlowPipeline",
|
| 3 |
+
"_mage_flow_version": "0.1.0",
|
| 4 |
+
"transformer": [
|
| 5 |
+
"mage_flow",
|
| 6 |
+
"MageFlow"
|
| 7 |
+
],
|
| 8 |
+
"vae": [
|
| 9 |
+
"mage_flow",
|
| 10 |
+
"MageVAE"
|
| 11 |
+
],
|
| 12 |
+
"text_encoder": [
|
| 13 |
+
"transformers",
|
| 14 |
+
"Qwen3VLForConditionalGeneration"
|
| 15 |
+
],
|
| 16 |
+
"tokenizer": [
|
| 17 |
+
"transformers",
|
| 18 |
+
"AutoProcessor"
|
| 19 |
+
],
|
| 20 |
+
"scheduler": [
|
| 21 |
+
"diffusers",
|
| 22 |
+
"FlowMatchEulerDiscreteScheduler"
|
| 23 |
+
],
|
| 24 |
+
"_text_encoder_path": "text_encoder",
|
| 25 |
+
"_vae_source": "vae/diffusion_pytorch_model.safetensors"
|
| 26 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.37.0",
|
| 4 |
+
"num_train_timesteps": 1000,
|
| 5 |
+
"use_dynamic_shifting": false,
|
| 6 |
+
"shift": 6.0
|
| 7 |
+
}
|
text_encoder/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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
|
text_encoder/README.md
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: image-text-to-text
|
| 4 |
+
library_name: transformers
|
| 5 |
+
---
|
| 6 |
+
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
|
| 7 |
+
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
|
| 8 |
+
</a>
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
# Qwen3-VL-4B-Instruct
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
|
| 15 |
+
|
| 16 |
+
This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.
|
| 17 |
+
|
| 18 |
+
Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment.
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
#### Key Enhancements:
|
| 22 |
+
|
| 23 |
+
* **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks.
|
| 24 |
+
|
| 25 |
+
* **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos.
|
| 26 |
+
|
| 27 |
+
* **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI.
|
| 28 |
+
|
| 29 |
+
* **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing.
|
| 30 |
+
|
| 31 |
+
* **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers.
|
| 32 |
+
|
| 33 |
+
* **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc.
|
| 34 |
+
|
| 35 |
+
* **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing.
|
| 36 |
+
|
| 37 |
+
* **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension.
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
#### Model Architecture Updates:
|
| 41 |
+
|
| 42 |
+
<p align="center">
|
| 43 |
+
<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_arc.jpg" width="80%"/>
|
| 44 |
+
<p>
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning.
|
| 48 |
+
|
| 49 |
+
2. **DeepStack**: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment.
|
| 50 |
+
|
| 51 |
+
3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling.
|
| 52 |
+
|
| 53 |
+
This is the weight repository for Qwen3-VL-4B-Instruct.
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
---
|
| 57 |
+
|
| 58 |
+
## Model Performance
|
| 59 |
+
|
| 60 |
+
**Multimodal performance**
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
**Pure text performance**
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
## Quickstart
|
| 68 |
+
|
| 69 |
+
Below, we provide simple examples to show how to use Qwen3-VL with 🤖 ModelScope and 🤗 Transformers.
|
| 70 |
+
|
| 71 |
+
The code of Qwen3-VL has been in the latest Hugging Face transformers and we advise you to build from source with command:
|
| 72 |
+
```
|
| 73 |
+
pip install git+https://github.com/huggingface/transformers
|
| 74 |
+
# pip install transformers==4.57.0 # currently, V4.57.0 is not released
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
### Using 🤗 Transformers to Chat
|
| 78 |
+
|
| 79 |
+
Here we show a code snippet to show how to use the chat model with `transformers`:
|
| 80 |
+
|
| 81 |
+
```python
|
| 82 |
+
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
|
| 83 |
+
|
| 84 |
+
# default: Load the model on the available device(s)
|
| 85 |
+
model = Qwen3VLForConditionalGeneration.from_pretrained(
|
| 86 |
+
"Qwen/Qwen3-VL-4B-Instruct", dtype="auto", device_map="auto"
|
| 87 |
+
)
|
| 88 |
+
|
| 89 |
+
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
|
| 90 |
+
# model = Qwen3VLForConditionalGeneration.from_pretrained(
|
| 91 |
+
# "Qwen/Qwen3-VL-4B-Instruct",
|
| 92 |
+
# dtype=torch.bfloat16,
|
| 93 |
+
# attn_implementation="flash_attention_2",
|
| 94 |
+
# device_map="auto",
|
| 95 |
+
# )
|
| 96 |
+
|
| 97 |
+
processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-4B-Instruct")
|
| 98 |
+
|
| 99 |
+
messages = [
|
| 100 |
+
{
|
| 101 |
+
"role": "user",
|
| 102 |
+
"content": [
|
| 103 |
+
{
|
| 104 |
+
"type": "image",
|
| 105 |
+
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
| 106 |
+
},
|
| 107 |
+
{"type": "text", "text": "Describe this image."},
|
| 108 |
+
],
|
| 109 |
+
}
|
| 110 |
+
]
|
| 111 |
+
|
| 112 |
+
# Preparation for inference
|
| 113 |
+
inputs = processor.apply_chat_template(
|
| 114 |
+
messages,
|
| 115 |
+
tokenize=True,
|
| 116 |
+
add_generation_prompt=True,
|
| 117 |
+
return_dict=True,
|
| 118 |
+
return_tensors="pt"
|
| 119 |
+
)
|
| 120 |
+
inputs = inputs.to(model.device)
|
| 121 |
+
|
| 122 |
+
# Inference: Generation of the output
|
| 123 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 124 |
+
generated_ids_trimmed = [
|
| 125 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 126 |
+
]
|
| 127 |
+
output_text = processor.batch_decode(
|
| 128 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 129 |
+
)
|
| 130 |
+
print(output_text)
|
| 131 |
+
```
|
| 132 |
+
|
| 133 |
+
### Generation Hyperparameters
|
| 134 |
+
#### VL
|
| 135 |
+
```bash
|
| 136 |
+
export greedy='false'
|
| 137 |
+
export top_p=0.8
|
| 138 |
+
export top_k=20
|
| 139 |
+
export temperature=0.7
|
| 140 |
+
export repetition_penalty=1.0
|
| 141 |
+
export presence_penalty=1.5
|
| 142 |
+
export out_seq_length=16384
|
| 143 |
+
```
|
| 144 |
+
|
| 145 |
+
#### Text
|
| 146 |
+
```bash
|
| 147 |
+
export greedy='false'
|
| 148 |
+
export top_p=1.0
|
| 149 |
+
export top_k=40
|
| 150 |
+
export repetition_penalty=1.0
|
| 151 |
+
export presence_penalty=2.0
|
| 152 |
+
export temperature=1.0
|
| 153 |
+
export out_seq_length=32768
|
| 154 |
+
```
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
## Citation
|
| 158 |
+
|
| 159 |
+
If you find our work helpful, feel free to give us a cite.
|
| 160 |
+
|
| 161 |
+
```
|
| 162 |
+
@misc{qwen3technicalreport,
|
| 163 |
+
title={Qwen3 Technical Report},
|
| 164 |
+
author={Qwen Team},
|
| 165 |
+
year={2025},
|
| 166 |
+
eprint={2505.09388},
|
| 167 |
+
archivePrefix={arXiv},
|
| 168 |
+
primaryClass={cs.CL},
|
| 169 |
+
url={https://arxiv.org/abs/2505.09388},
|
| 170 |
+
}
|
| 171 |
+
|
| 172 |
+
@article{Qwen2.5-VL,
|
| 173 |
+
title={Qwen2.5-VL Technical Report},
|
| 174 |
+
author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang},
|
| 175 |
+
journal={arXiv preprint arXiv:2502.13923},
|
| 176 |
+
year={2025}
|
| 177 |
+
}
|
| 178 |
+
|
| 179 |
+
@article{Qwen2VL,
|
| 180 |
+
title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
|
| 181 |
+
author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
|
| 182 |
+
journal={arXiv preprint arXiv:2409.12191},
|
| 183 |
+
year={2024}
|
| 184 |
+
}
|
| 185 |
+
|
| 186 |
+
@article{Qwen-VL,
|
| 187 |
+
title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
|
| 188 |
+
author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
|
| 189 |
+
journal={arXiv preprint arXiv:2308.12966},
|
| 190 |
+
year={2023}
|
| 191 |
+
}
|
| 192 |
+
```
|
text_encoder/chat_template.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
| 4 |
+
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 151655,
|
| 6 |
+
"model_type": "qwen3_vl",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 151645,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 2560,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 9728,
|
| 18 |
+
"max_position_embeddings": 262144,
|
| 19 |
+
"model_type": "qwen3_vl_text",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 36,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"mrope_interleaved": true,
|
| 26 |
+
"mrope_section": [
|
| 27 |
+
24,
|
| 28 |
+
20,
|
| 29 |
+
20
|
| 30 |
+
],
|
| 31 |
+
"rope_type": "default"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 5000000,
|
| 34 |
+
"tie_word_embeddings": true,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 151936
|
| 37 |
+
},
|
| 38 |
+
"tie_word_embeddings": true,
|
| 39 |
+
"transformers_version": "4.57.0.dev0",
|
| 40 |
+
"video_token_id": 151656,
|
| 41 |
+
"vision_config": {
|
| 42 |
+
"deepstack_visual_indexes": [
|
| 43 |
+
5,
|
| 44 |
+
11,
|
| 45 |
+
17
|
| 46 |
+
],
|
| 47 |
+
"depth": 24,
|
| 48 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 49 |
+
"hidden_size": 1024,
|
| 50 |
+
"in_channels": 3,
|
| 51 |
+
"initializer_range": 0.02,
|
| 52 |
+
"intermediate_size": 4096,
|
| 53 |
+
"model_type": "qwen3_vl",
|
| 54 |
+
"num_heads": 16,
|
| 55 |
+
"num_position_embeddings": 2304,
|
| 56 |
+
"out_hidden_size": 2560,
|
| 57 |
+
"patch_size": 16,
|
| 58 |
+
"spatial_merge_size": 2,
|
| 59 |
+
"temporal_patch_size": 2
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652
|
| 63 |
+
}
|
text_encoder/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"repetition_penalty": 1.0,
|
| 12 |
+
"temperature": 0.7,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
text_encoder/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
text_encoder/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30a01a0556622645a3cce87b655bbbbbc1f170c196099f1b666c93202c3339a9
|
| 3 |
+
size 4967229296
|
text_encoder/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:046296a2a387efb43b0c997d5833c789604d168834f6e0d3064bf7bb13d002a6
|
| 3 |
+
size 3908490048
|
text_encoder/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,720 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8875631616
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 719 |
+
}
|
| 720 |
+
}
|
text_encoder/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
text_encoder/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
text_encoder/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
text_encoder/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
text_encoder/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"in_channels": 128,
|
| 3 |
+
"out_channels": 128,
|
| 4 |
+
"vec_in_dim": 0,
|
| 5 |
+
"context_in_dim": 2560,
|
| 6 |
+
"hidden_size": 3072,
|
| 7 |
+
"mlp_ratio": 4.0,
|
| 8 |
+
"num_heads": 24,
|
| 9 |
+
"depth": 12,
|
| 10 |
+
"depth_single_blocks": 0,
|
| 11 |
+
"axes_dim": [
|
| 12 |
+
16,
|
| 13 |
+
56,
|
| 14 |
+
56
|
| 15 |
+
],
|
| 16 |
+
"theta": 10000,
|
| 17 |
+
"patch_size": 1,
|
| 18 |
+
"qkv_bias": true,
|
| 19 |
+
"guidance_embed": false,
|
| 20 |
+
"checkpoint": false,
|
| 21 |
+
"rope_type": "msrope",
|
| 22 |
+
"time_type": "qwen_proj",
|
| 23 |
+
"double_block_type": "double_stream",
|
| 24 |
+
"vec_type": null,
|
| 25 |
+
"apply_text_rotary_emb": false,
|
| 26 |
+
"_class_name": "MageFlow",
|
| 27 |
+
"txt_max_length": 2048,
|
| 28 |
+
"max_sequence_length": 2048,
|
| 29 |
+
"param_dtype": "bfloat16",
|
| 30 |
+
"packing": true,
|
| 31 |
+
"schedule_mode": "z-image",
|
| 32 |
+
"static_shift": 6.0,
|
| 33 |
+
"use_time_shift": false
|
| 34 |
+
}
|
transformer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04431abbc3acd1a5b86a7f77269f8e77e05a6cac3b21f35e1aef7493f6ab4934
|
| 3 |
+
size 8231536784
|
vae/config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MageVAE",
|
| 3 |
+
"latent_channels": 128,
|
| 4 |
+
"downsample_factor": 16,
|
| 5 |
+
"sample_posterior": false
|
| 6 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34e076dc1e8a15321e1e07be5111d59cf16dd10b804b7c7e20b4de29013427e0
|
| 3 |
+
size 345053056
|