Update README.md

README.md

@@ -1,4 +1,5 @@
-Mistral 7B with step-by-step PPO supervised by [Math-Shepherd](https://arxiv.org/pdf/2312.08935.pdf). We use questions in MetaMATH [1] for PPO training.
+Mistral 7B with step-by-step PPO supervised by [math-shepherd-mistral-7b-prm](https://huggingface.co/peiyi9979/math-shepherd-mistral-7b-prm). We use questions in MetaMATH [1] for PPO training.
+The model is initiated with [mistral-7b-sft](https://huggingface.co/peiyi9979/mistral-7b-sft).
 
 Pass@1:
 - GSM8K: 84.1