Update app.py

app.py

@@ -10,10 +10,7 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message
 ):
     especificacion = '''
     Eres un experto en large language models (LLM), tanto en la base conceptual de entrenamiento de modelos, como las arquitecturas \
@@ -47,11 +44,7 @@ def respond(
         yield response
 
 demo = gr.ChatInterface(
-    respond,
-    
-    additional_inputs=[
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="max_tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="temperature"),
+    respond
     ]
 )