Update app.py

app.py

@@ -21,8 +21,8 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
     response = model(
         prompt, 
         max_tokens=max_tokens, 
-        temperature=temperature, 
-        top_p=top_p
+        # temperature=temperature, 
+        # top_p=top_p
     )
 
     # Extract text response
@@ -33,9 +33,9 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a helpful AI assistant.", label="System message"),
-        gr.Slider(minimum=10, maximum=512, value=100, step=10, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=1.5, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.75, step=0.05, label="Top-p (nucleus sampling)"),
+        gr.Slider(minimum=10, maximum=1024, value=256, step=10, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=1.5, value=0.7, step=0.1, label="Temperature no effect"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p (nucleus sampling) no effect"),
     ],
 )