Update app.py

app.py

@@ -47,7 +47,6 @@ def respond(
         output = ""
         for chunk in stream:
             delta = chunk.choices[0].delta
-            print(delta)
             
             try:
                 output += delta.reasoning_content
@@ -61,14 +60,8 @@ def respond(
         yield "⚠️ Llama.cpp server error"
 
 demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="", label="System message"),
-        gr.Slider(minimum=1, maximum=8000, value=4096, 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, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
-    ],
+    respond
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(show_api=False)