Update README.md

README.md

@@ -16,6 +16,9 @@ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/m
 I think SPIN not only can use on a SFT model, but also it  can use on a pretrained model. 
 Therefore, I use SPIN on a pretrained model microsoft/phi-2. And I get a higher score better than origin pretrained model. You can check the [open llm leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
 
+The best paradigm for training a conversational Large Language Model (LLM):
+pretrain -> dpo(spin) -> sft -> dpo(spin)
+
 ## Training procedure
 
 ### Training hyperparameters