change model AI

app.py

@@ -13,7 +13,7 @@ async def generate_response(user_input):
     ]
 
     response = client.chat.completions.create(
-        model= 'nvidia/Llama-3.1-Nemotron-70B-Instruct-HF',
+        model= 'meta-llama/Llama-3.1-70B-Instruct',
         messages=messages, 
         max_tokens=16384,
         max_completion_tokens=16384