rasyosef commited on
Commit
26f43ad
1 Parent(s): 3743409

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -3
app.py CHANGED
@@ -64,11 +64,12 @@ with gr.Blocks() as demo:
64
  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.
65
  """)
66
 
67
- 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.")
68
-
69
  chatbot = gr.ChatInterface(
70
  fn=generate,
71
- additional_inputs=[tokens_slider],
 
 
72
  stop_btn=None,
73
  examples=[["Who is Leonhard Euler?"]]
74
  )
 
64
  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.
65
  """)
66
 
67
+
 
68
  chatbot = gr.ChatInterface(
69
  fn=generate,
70
+ additional_inputs=[
71
+ 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.")
72
+ ],
73
  stop_btn=None,
74
  examples=[["Who is Leonhard Euler?"]]
75
  )