Update README.md

README.md

@@ -21,7 +21,7 @@ BPO is a black-box alignment technique that differs from training-based methods
 
 ### Data
 Prompt优化模型由隐含人类偏好特征的prompt优化对训练得到，数据集的详细信息在这里。
-The Prompt Optimization Model is trained on prompt optimization pairs which contain human preference features. Detailed information on the dataset can be found [here](https://huggingface.co/datasets/CCCCCC/BPO).
+The Prompt Optimization Model is trained on prompt optimization pairs which contain human preference features. Detailed information on the dataset can be found [here](https://huggingface.co/datasets/THUDM/BPO).
 
 ### Backbone Model
 The prompt preference optimizer is built on `Llama-2-7b-chat-hf`.