Update app.py

app.py

@@ -8,7 +8,7 @@ system_prompt = """Your system prompt here"""
 def format_prompt(history):
     return system_prompt + "\n\n" + "\n".join([f"User: {h[0]}\nAssistant: {h[1]}" for h in history])
 
-def predict(inputs, history, temperature, max_new_tokens, top_p, repetition_penalty):
+def predict(inputs, history, temperature=0.9, max_new_tokens=256, top_p=0.9, repetition_penalty=1.0):
     prompt = format_prompt(history + [[inputs, ""]])
     response = inference.text_generation(prompt, temperature=temperature, max_new_tokens=max_new_tokens, top_p=top_p, repetition_penalty=repetition_penalty)
     history.append([inputs, response])
@@ -35,6 +35,9 @@ body {
 .gr-button:hover {
     background-color: #d81b60;
 }
+footer {
+    display: none;
+}
 """
 
 with gr.Blocks(css=css) as demo:
@@ -44,13 +47,8 @@ with gr.Blocks(css=css) as demo:
     with gr.Row():
         txt = gr.Textbox(show_label=False, placeholder="Type a message...")
         submit_btn = gr.Button("Submit")
-    with gr.Accordion("Settings", open=False):
-        temperature = gr.Slider(0, 1, value=0.9, step=0.1, label="Temperature")
-        max_new_tokens = gr.Slider(0, 500, value=256, step=10, label="Max New Tokens")
-        top_p = gr.Slider(0, 1, value=0.9, step=0.1, label="Top P")
-        repetition_penalty = gr.Slider(1, 2, value=1.0, step=0.1, label="Repetition Penalty")
-
-    submit_btn.click(predict, [txt, chatbot, temperature, max_new_tokens, top_p, repetition_penalty], [chatbot, chatbot])
-    txt.submit(predict, [txt, chatbot, temperature, max_new_tokens, top_p, repetition_penalty], [chatbot, chatbot])
+
+    submit_btn.click(predict, [txt, chatbot], [chatbot, chatbot])
+    txt.submit(predict, [txt, chatbot], [chatbot, chatbot])
 
 demo.launch()