Update README.md

README.md

@@ -33,23 +33,23 @@ This model was built using the Smaug recipe  for improving performance on real w
 ########## First turn ##########
                    score
 model             turn
-Llama-3-Smaug-8B 1   8.79375
-Meta-Llama-3-8B-Instruct 1   8.53125
+Llama-3-Smaug-8B 1   8.77500
+Meta-Llama-3-8B-Instruct 1   8.1
 ########## Second turn ##########
                    score
 model             turn
-Llama-3-Smaug-8B 2   7.7250
-Meta-Llama-3-8B-Instruct 2   7.5500
+Meta-Llama-3-8B-Instruct 2   8.2125
+Llama-3-Smaug-8B 2   7.8875
 ########## Average ##########
                  score
 model
-Llama-3-Smaug-8B  8.259375
-Meta-Llama-3-8B-Instruct 8.040625
+Llama-3-Smaug-8B  8.331250
+Meta-Llama-3-8B-Instruct 8.15625
 ```
 
 | Model | First turn | Second Turn | Average |
 | :---- | ---------: | ----------: | ------: |
-| Llama-3-Smaug-8B | 8.79 | 7.73 | 8.26 |
-| Llama-3-8B-Instruct | 8.53 |  7.55 | 8.04 |
+| Llama-3-Smaug-8B | 8.78 | 7.89 | 8.33 |
+| Llama-3-8B-Instruct | 8.1 |  8.21 | 8.16 |
 
 This version of Smaug uses new techniques and new data compared to [Smaug-72B](https://huggingface.co/abacusai/Smaug-72B-v0.1), and more information will be released later on. For now, see the previous Smaug paper: https://arxiv.org/abs/2402.13228.