Update README.md

README.md

@@ -10,9 +10,9 @@ model-index:
 ---
 
 # una-llama-7b
+**UNA: Uniform Neural Alignment** It increases 6.75% the performance of the pre-trained base LLaMA (1) 7B.
 
-This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on the allenai/ultrafeedback_binarized_cleaned dataset.
-It achieves the following results on the evaluation set:
+This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b):
 - Loss: 0.5529
 - Rewards/chosen: 0.3633
 - Rewards/rejected: -0.1873