Update README.md

README.md

@@ -8,4 +8,6 @@ base_model:
 - princeton-nlp/Llama-3-Base-8B-SFT
 ---
 
-This is an algined model based on princeton-nlp/Llama-3-Base-8B-SFT. More information will be added later.
+This is an algined model based on princeton-nlp/Llama-3-Base-8B-SFT. The alignment loss has two parts, preference loss and a regularization term.
+
+More information will be added later.