Update README.md

README.md

@@ -17,13 +17,13 @@ datasets:
 
 ## Update
 
-- 2025/09/24: We present **Qwen-Image-12B**, an open-source pruned variant with 12B parameters. Experimental results show that its performance is on par with the prior 13.3B model pruned by removing 20 layers, as validated through both objective benchmarks and human assessment. Continuous optimization efforts are underway. 
+- 2025/09/24: We present **Qwen-Image-12B**, an open-source pruned variant with 12.7B parameters. Experimental results show that its performance is on par with the prior 13.6B model pruned by removing 20 layers, as validated through both objective benchmarks and human assessment. Continuous optimization efforts are underway. 
 
 
 
 
 ## Introduction
-This open-source project is based on Qwen-Image and has attempted model pruning, removing 20 layers while retaining the weights of 40 layers, resulting in a model size of 13.3B parameters. The pruned model has experienced a slight drop in objective metrics. The pruned version will continue to be iterated upon. Additionally, the pruned version supports the adaptation and loading of community models such as LoRA and ControlNet. Please stay tuned. For the relevant inference scripts, please refer to **[Qwen-Image-Pruning](https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning)**.
+This open-source project is based on Qwen-Image 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 model has experienced a slight drop in objective metrics. The pruned version will continue to be iterated upon. Additionally, the pruned version supports the adaptation and loading of community models such as LoRA and ControlNet. Please stay tuned. For the relevant inference scripts, please refer to **[Qwen-Image-Pruning](https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning)**.
 
 <div align="center">
   <img src="bench.png">