Add MT-Bench performance

README.md

@@ -74,6 +74,17 @@ print(tokenizer.decode(outputs[0]))
 |RoLlama2-7b-Instruct| **44.42**|**40.36** |**37.41** |**69.58** | 55.64    | **17.59**| 45.96    |  
 |RoLlama2-7b-Chat    | 42.65    | 38.29    | 35.27    | 65.25    | **56.45**| 12.84    | **47.79**|  
 
+## MT-Bench
+
+| Model              | Average  | 1st turn      | 2nd turn     |
+|--------------------|:--------:|:--------:|:--------:|
+| Llama-2-7b-chat    | 1.70    | 2.00    | 1.41    |
+|RoLlama2-7b-Instruct| **4.31**|**5.66** |**2.95** |
+|RoLlama2-7b-Chat    | 3.91    | 4.25    | 3.57    |
+
+
+
+
 ## Citation 
 
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->