Update README.md

README.md

@@ -18,8 +18,7 @@ If you have any question with this reward model and also any question about rewa
 
 <!-- Provide a longer summary of what this model is. -->
 
-The model is trained on a mixture of the dataset similar to [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it).
-
+The model is trained on a mixture of the following datasets. We also provide the mixture in [weqweasdas/preference_dataset_mixture2_and_safe_pku](weqweasdas/preference_dataset_mixture2_and_safe_pku).
 - [HH-RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf)
 - [SHP](https://huggingface.co/datasets/stanfordnlp/SHP)
 - [UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback)