Update app.py

app.py

@@ -83,7 +83,7 @@ async def generate_response(message):
 
     loop = asyncio.get_event_loop()
     response = await loop.run_in_executor(None, lambda: hf_client.chat_completion(
-        messages, max_tokens=1000, stream=True, temperature=0.7, top_p=0.85))
+        messages, max_tokens=500, stream=True, temperature=0.7, top_p=0.85))
 
     full_response = []
     for part in response: