Update app.py

app.py

@@ -14,7 +14,7 @@ def generate_response(question, prompt):
     
     # Get the completion from the model
     completion = client.chat.completions.create(
-        model="meta-llama/Llama-3.1-8B-Instruct", 
+        model="meta-llama/Meta-Llama-3-8B-Instruct", 
         messages=messages, 
         max_tokens=1024
     )