Update README.md

README.md

@@ -39,7 +39,7 @@ We evaluate our reward model on the [JudgeBench](https://huggingface.co/datasets
 
 ## Usage
 
-You can directly run the GRAM model using the demo provided below. You can also train GRAM using the code available [here](https://github.com/wangclnlp/GRAM/tree/main).
+You can directly run the GRAM model using the demo provided below. You can also train GRAM using the code available [here](https://github.com/NiuTrans/GRAM).
 
 ```python
 import torch