change model

app.py

@@ -2,9 +2,6 @@ import gradio as gr
 import os
 from openai import OpenAI
 
-API_URL = "https://api-inference.huggingface.co/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
-headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}
-
 async def generate_response(user_input):
     client = OpenAI(
         base_url="https://api-inference.huggingface.co/v1/",
@@ -16,10 +13,9 @@ async def generate_response(user_input):
     ]
 
     response = client.chat.completions.create(
-        model="meta-llama/Llama-3.1-70B-Instruct", 
+        model= 'nvidia/Llama-3.1-Nemotron-70B-Instruct-HF',
         messages=messages, 
-        max_tokens=500,
-        stream=False
+        max_tokens= 500,
     )
 
     return response.choices[0].message.content