Reducing default token generation to 15 tokens to prevent the model from taking too long to respond.

app.py

@@ -70,7 +70,7 @@ demo = gr.ChatInterface(
     type='messages',
     additional_inputs=[
         gr.Dropdown(choices=["DialoGPT-med-FT", "DialoGPT-medium"], value="DialoGPT-med-FT", label="Model"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=100, value=15, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],