Update README.md

README.md

@@ -10,4 +10,4 @@ language:
 
 The extrapolated (ExPO) model based on [`allenai/tulu-2-dpo-13b`](https://huggingface.co/allenai/tulu-2-dpo-13b) and [`allenai/tulu-2-13b`](https://huggingface.co/allenai/tulu-2-13b), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
 
-Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
+Specifically, we obtain this model by extrapolating **(alpha = 0.5)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.