Update main.py

main.py

@@ -34,7 +34,6 @@ class ChatCompletionRequest(BaseModel):
 async def chat(request: ChatCompletionRequest, response_mode=None):
     tokens = llm.tokenize(request.prompt)
     async def server_sent_events(chat_chunks, llm):
-        yield prompt
         for chat_chunk in llm.generate(chat_chunks):
             yield llm.detokenize(chat_chunk)
         yield ""