Update app.py

app.py

@@ -212,7 +212,8 @@ async def generate_text(request: RequestModel):
     {"role": "user", "content": instructions_par_defaut + request.text}
     ]
     completion = client.chat.completions.create(
-        model="nvidia/llama-3.1-nemotron-70b-instruct", 
+        # model="nvidia/llama-3.1-nemotron-70b-instruct", 
+        model="nv-mistralai/mistral-nemo-12b-instruct"
         messages=messages,
         # max_tokens=1024, 
         stream=True