fix

main.py

@@ -128,7 +128,7 @@ system_message = "Below is a conversation between a human user and a helpful AI
 @app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
     dialogue_template = DialogueTemplate(
-        system=system_message, messages=[request.messages]
+        system=system_message, messages=request.messages
     )
     prompt = dialogue_template.get_inference_prompt()
     tokens = llm.tokenize(prompt)