Update README.md

README.md

@@ -3,7 +3,7 @@ license: mit
 datasets:
 - HuggingFaceH4/ultrafeedback_binarized
 base_model:
-- meta-llama/Llama-3.1-8B
+- princeton-nlp/Llama-3-Base-8B-SFT
 ---
 
-This is an aligned model based on princeton-nlp/Llama-3-Base-8B-SFT. This model is aligned using the Ultrafeedback dataset, fine-tuned through the Simple Preference Optimization (SimPO) loss. The optimization process was conducted with a single epoch. 
+This is an aligned model based on princeton-nlp/Llama-3-Base-8B-SFT. This model is aligned using the Ultrafeedback dataset, fine-tuned through the Simple Preference Optimization (SimPO) loss. The optimization process was conducted with a single epoch.