Update app.py

app.py

@@ -18,7 +18,7 @@ model.to(device)
 MAX_INPUT_TOKEN_LENGTH = 4096  # You may need to adjust this value
 
 @spaces.GPU
-def generate(
+def respond(
     message: str,
     chat_history: list[tuple[str, str]],
     system_prompt: str,
@@ -62,17 +62,23 @@ def generate(
         yield "".join(outputs)
 
 demo = gr.ChatInterface(
-    generate,
+    respond,
     additional_inputs=[
-        gr.Textbox(value="You are Magpie, a friendly Chatbot.", label="System prompt"),
-        gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Max new tokens"),
+        gr.Textbox(value="You are Magpie, a helpful AI assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p"),
-        gr.Slider(minimum=1, maximum=100, value=50, step=1, label="Top-k"),
-        gr.Slider(minimum=0.5, maximum=2.0, value=1.2, step=0.1, label="Repetition Penalty"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.9,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+        gr.Slider(minimum=0.5, maximum=1.5, value=1.0, step=0.1, label="Repetation Penalty"),
     ],
 )
 
+
 if __name__ == "__main__":
     demo.queue()
     demo.launch(share=True)