Update README.md

README.md

@@ -11,10 +11,22 @@ This is one of the first models trained on the LosslessMegaCodeTrainingV2_1m_Evo
 
 This model is extremely good at coding, and might be one of the best coding models for its size and much better than any 7b parameter model. Plans for bigger models are coming in the future.
 
-The chat format for this model is alpaca
+### Prompt template
+
+[chatml](https://github.com/openai/openai-python/blob/main/chatml.md) format is used:
+"<|im_start|>system\n{system message}<|im_end|>\n<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n" 
+
+multi-line:
+
 ```
-USER: {prompt}
-ASSISTANT:
+"""
+<|im_start|>system
+{system message}<|im_end|>
+<|im_start|>user
+{user prompt}<|im_end|>
+<|im_start|>assistant
+{Assistant answer}<|im_end|>
+"""
 ```
 
 The link for the full dataset is bellow: