Update README.md

README.md

@@ -6,7 +6,7 @@
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-The reward model is trained from the base model [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it). 
+The reward model is trained from the base model [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2). 
 
 The training script is available at https://github.com/WeiXiongUST/RLHF-Reward-Modeling .
 
@@ -18,7 +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 [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it).
+The model is trained on a mixture of the dataset similar to [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it).
 
 - [HH-RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf)
 - [SHP](https://huggingface.co/datasets/stanfordnlp/SHP)