Refactoriza la función `respond` en `app.py` para establecer valores predeterminados para `system_message`, `max_tokens`, `temperature` y `top_p`. Elimina los inputs adicionales en la interfaz de chat y habilita el modo de depuración en el lanzamiento de la aplicación.

app.py

@@ -5,15 +5,17 @@ from huggingface_hub import InferenceClient
 def respond(
     message,
     history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
     hf_token: gr.OAuthToken,
 ):
     """
     For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
+    # Configuración por defecto
+    system_message = "You are a friendly Chatbot."
+    max_tokens = 512
+    temperature = 0.7
+    top_p = 0.95
+
     client = InferenceClient(token=hf_token.token, model="openbmb/MiniCPM-V-4_5")
 
     messages = [{"role": "system", "content": system_message}]
@@ -46,18 +48,6 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
 )
 
 with gr.Blocks() as demo:
@@ -67,4 +57,6 @@ with gr.Blocks() as demo:
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(
+        debug=True,  # Habilita recarga automática y debugging
+    )