max_tokens

app.py

@@ -84,7 +84,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Slider(minimum=1, maximum=8192, value=6144, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=4096, value=2048, 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,