Update app.py

app.py

@@ -61,17 +61,22 @@ def gradio_predict(user_message, system_message, max_new_tokens, temperature, to
 
 Tulu_bot = TuluChatBot(model, tokenizer)
 
+
 with gr.Blocks() as demo:
     with gr.Row():
         user_message = gr.Textbox(label="Your Message", lines=3)
         system_message = gr.Textbox(label="Introduce a Character Here or Set a Scene (system prompt)", lines=2)
     with gr.Row():
         do_sample = gr.Checkbox(label="Advanced", value=False)
-    with gr.Row(visible=lambda do_sample: do_sample):
-        max_new_tokens = gr.Slider(label="Max new tokens", value=1269, minimum=550, maximum=3200, step=1)
-        temperature = gr.Slider(label="Temperature", value=1.2, minimum=0.05, maximum=4.0, step=0.05)
-        top_p = gr.Slider(label="Top-p (nucleus sampling)", value=0.90, minimum=0.01, maximum=0.99, step=0.05)
-        repetition_penalty = gr.Slider(label="Repetition penalty", value=1.9, minimum=1.0, maximum=2.0, step=0.05)
+    
+    # Advanced settings in an Accordion
+    with gr.Accordion("Advanced Settings", open=False).style(visible=lambda do_sample: do_sample):
+        with gr.Row():
+            max_new_tokens = gr.Slider(label="Max new tokens", value=1269, minimum=550, maximum=3200, step=1)
+            temperature = gr.Slider(label="Temperature", value=1.2, minimum=0.05, maximum=4.0, step=0.05)
+            top_p = gr.Slider(label="Top-p (nucleus sampling)", value=0.90, minimum=0.01, maximum=0.99, step=0.05)
+            repetition_penalty = gr.Slider(label="Repetition penalty", value=1.9, minimum=1.0, maximum=2.0, step=0.05)
+
     submit_button = gr.Button("Submit")
     output_text = gr.Textbox()