update

app.py

@@ -213,8 +213,6 @@ async def generate_text(request: RequestModel):
     completion = client.chat.completions.create(
         model="meta/llama-3.1-8b-instruct", 
         messages=messages,
-        temperature=0.2,
-        top_p=0.9,
         # max_tokens=1024, 
         stream=True
     )