Use Llama3 end point.

app.py

@@ -3,9 +3,9 @@ import gradio as gr
 import json
 
 def get_text_response(prompt):
-    api_url = "http://35.233.231.20:5002/api/generate"
+    api_url = "http://35.233.231.20:5003/api/generate"
     data_payload = {
-        "model": "llama2",
+        "model": "llama3",
         "prompt": prompt,
         "stream": True
     }