Update app.py

app.py

@@ -64,11 +64,12 @@ with gr.Blocks() as demo:
   In order to reduce the response time on this hardware, `max_new_tokens` has been set to `21` in the text generation pipeline. With this default configuration, it takes approximately `60 seconds` for the response to start being generated, and streamed one word at a time. Use the slider below to increase or decrease the length of the generated text.
   """)
 
-  tokens_slider = gr.Slider(8, 128, value=21, 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.")
-
+  
   chatbot = gr.ChatInterface(
     fn=generate,
-    additional_inputs=[tokens_slider],
+    additional_inputs=[
+        gr.Slider(8, 128, value=21, 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.")
+    ],
     stop_btn=None,
     examples=[["Who is Leonhard Euler?"]]
   )