Update README.md

README.md

@@ -70,6 +70,17 @@ Score 5: {score5_description}
 ###Feedback: 
 ```
 
+After this, you should apply the conversation template of Llama-2-Chat (not applying it might lead to unexpected behaviors)
+```
+conv = get_conv_template("llama-2")
+conv.set_system_message("You are a fair evaluator language model.")
+conv.append_message(conv.roles[0], dialogs['instruction'])
+conv.append_message(conv.roles[1], None)
+prompt = conv.get_prompt()
+
+x = tokenizer(prompt,truncation=False)
+```
+
 As a result, a feedback and score decision will be generated, divided by a separating phrase ```[RESULT]``` 
 
 ## License