Update README.md

README.md

@@ -155,7 +155,8 @@ For instruction training, we first trained the model with Supervised Fine-tuning
 {The model's response}</s>
 ```
 
-When prompting the model for a response, your input should be structured as follows:
+> [!IMPORTANT]
+> When prompting the model for a response, your input should be structured as follows:
 
 ```
 <s>system\n