Update README.md

README.md

@@ -81,22 +81,23 @@ We evaluated checkpoint 1000 ([abacusai/Liberated-Qwen1.5-72B-c1000](https://hug
                                         score
 model                           turn
 Liberated-Qwen-1.5-72b-ckpt1000 1     8.45000
-Smaug-72B-v0.1                  1     8.21250
+Qwen1.5-72B-Chat                1     8.44375
+
 
 ########## Second turn ##########
                                         score
 model                           turn
+Qwen1.5-72B-Chat                2     8.23750
 Liberated-Qwen-1.5-72b-ckpt1000 2     7.65000
-Smaug-72B-v0.1                  2     7.20625
+
 
 ########## Average ##########
                                     score
 model
+Qwen1.5-72B-Chat                 8.340625
 Liberated-Qwen-1.5-72b-ckpt1000  8.050000
-Smaug-72B-v0.1                   7.709375
-```
 
-Smaug has a higher leaderboard average score, but it appears that this new dataset does significantly help with instruction following.
+```
 
 The model does preserve good performance on MMLU = 77.13.