Switch to Groq llama-3.1-8b-instant via LiteLLM

app.py

@@ -69,7 +69,7 @@ CRITICAL RULES:
 
 def build_agent():
     model = InferenceClientModel(
-        model_id="meta-llama/Llama-3.1-8B-Instruct",
+        model_id="groq/llama-3.1-8b-instant",
         token=os.getenv("HF"),
         max_tokens=1024,
     )