Update app.py

app.py

@@ -39,7 +39,6 @@ llm = Llama.from_pretrained(
   n_ctx=2048, # n_ctx should be increased to accommodate the image embedding
 )
 
-
 @spaces.GPU(queue=False)
 def stream_chat(message, history: list, temperature: float, max_new_tokens: int):
     print(f'message is - {message}')
@@ -92,7 +91,6 @@ def stream_chat(message, history: list, temperature: float, max_new_tokens: int)
         messages = messages,
         temperature=temperature,
         max_tokens=max_new_tokens,
-        stream=True
     )
 
     return response["choices"][0]["text"]