Update README.md

README.md

@@ -18,20 +18,20 @@ language:
 <!-- header end -->
 
 # Model Description
-This model finetuned [trinity-v1](https://huggingface.co/jan-hq/trinity-v1) on [ultrafeedback_binarized_subset](jan-hq/ultrafeedback_binarized_subset) (cleaned version)
+This model finetuned [trinity-v1](https://huggingface.co/jan-hq/trinity-v1) on [ultrafeedback_binarized_subset](jan-hq/ultrafeedback_binarized_subset)
+ (cleaned version)
 
 More details about the training result [here](https://huggingface.co/jan-hq/trinity-v1-dpo-adapter).
 
 # Prompt template
 
-- **ChatML**
-
 ```
-<|im_start|>system
-{system_message}<|im_end|>
-<|im_start|>user
-{prompt}<|im_end|>
-<|im_start|>assistant
+{system_message}
+### Instruction:
+{prompt}
+
+### Response:
+
 ```
 
 # Run this model