Update README.md

README.md

@@ -21,9 +21,9 @@ Doge uses `wsd_scheduler` as the training scheduler, which divides the learning
 
 Here are the initial learning rates required to continue training at each checkpoint:
 
-- **[Doge-20M](https://huggingface.co/JingzeShi/Doge-20M-checkpoint)**: 8e-3
-- **[Doge-60M](https://huggingface.co/JingzeShi/Doge-60M-checkpoint)**: 6e-3
-- **[Doge-160M](https://huggingface.co/JingzeShi/Doge-160M-checkpoint)**: 4e-3
+- **[Doge-20M](https://huggingface.co/SmallDoge/Doge-20M-checkpoint)**: 8e-3
+- **[Doge-60M](https://huggingface.co/SmallDoge/Doge-60M-checkpoint)**: 6e-3
+- **[Doge-160M](https://huggingface.co/SmallDoge/Doge-160M-checkpoint)**: 4e-3
 - **Doge-320M**: 2e-3
 
 | Model | Learning Rate | Schedule | Warmup Steps | Stable Steps |