Update README.md
Browse files
README.md
CHANGED
|
@@ -15,13 +15,18 @@ datasets:
|
|
| 15 |
<a href='https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning'><img src="https://img.shields.io/badge/GitHub-OPPOer-blue.svg?logo=github" alt="GitHub"></a>
|
| 16 |
</div>
|
| 17 |
|
|
|
|
|
|
|
|
|
|
| 18 |
## Introduction
|
| 19 |
This open-source project is based on Qwen-Image-Edit and has attempted model pruning, removing 20 layers while retaining the weights of 40 layers, resulting in a model size of 13.6B parameters. The pruned version will continue to be iterated upon. Please stay tuned.
|
| 20 |
|
| 21 |
<div align="center">
|
| 22 |
<img src="bench.png">
|
| 23 |
</div>
|
| 24 |
-
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Quick Start
|
| 27 |
|
|
|
|
| 15 |
<a href='https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning'><img src="https://img.shields.io/badge/GitHub-OPPOer-blue.svg?logo=github" alt="GitHub"></a>
|
| 16 |
</div>
|
| 17 |
|
| 18 |
+
## Update
|
| 19 |
+
- 2025/09/29: We release **Qwen-Image-Edit-2509-Pruning**
|
| 20 |
+
-
|
| 21 |
## Introduction
|
| 22 |
This open-source project is based on Qwen-Image-Edit and has attempted model pruning, removing 20 layers while retaining the weights of 40 layers, resulting in a model size of 13.6B parameters. The pruned version will continue to be iterated upon. Please stay tuned.
|
| 23 |
|
| 24 |
<div align="center">
|
| 25 |
<img src="bench.png">
|
| 26 |
</div>
|
| 27 |
+
<div align="center">
|
| 28 |
+
<img src="bench-2509.png">
|
| 29 |
+
</div>
|
| 30 |
|
| 31 |
## Quick Start
|
| 32 |
|