updated app.py.

app.py

@@ -1,7 +1,4 @@
 from huggingface_hub import InferenceClient
-import os
-
-HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 client = InferenceClient(
     "meta-llama/Meta-Llama-3-8B-Instruct"
@@ -84,5 +81,6 @@ gr.ChatInterface(
     examples=[
         ["Can you explain briefly to me what is the Python programming language?"],
         ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
-    ]
+    ],
+    cache_examples=True
 ).launch(show_api=False)