Update app.py

app.py

@@ -82,8 +82,8 @@ with gr.Blocks() as demo:
 
     tokens_slider = gr.Slider(
         8,
-        128,
-        value=21,
+        512,
+        value=256,
         label="Maximum new tokens",
         info="A larger `max_new_tokens` parameter value gives you longer text responses but at the cost of a slower response time.",
     )