Update README.md

README.md

@@ -97,7 +97,7 @@ model-index:
       name: accuracy
 ---
 
-# Model Card for Gemma 2B Zephyr SFT
+# Model Card for Gemma 2B Zephyr DPO
 
 We trained the [google/gemma-2b](https://huggingface.co/google/gemma-2b) with DPO and data from `argilla/dpo-mix-7k`.
 We carefully selected the hyper-parameters to achieve the best DPO performance.