One more try to get inference llama 3.2 model working

app.py

@@ -27,7 +27,7 @@ if st.button("Submit"):
 
         completion = client.chat.completions.create(
             #model="Qwen/Qwen2.5-Coder-32B-Instruct", 
-            model="meta-llama/LLaMA-3-8b",
+            model="meta-llama/Llama-3.2-3B-Instruct",
         	messages=messages, 
         	max_tokens=500
         )