hopefully

app.py

@@ -8,10 +8,7 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
 def respond(
-    message,
-    max_tokens,
-    temperature,
-    top_p,
+    message
 ):
     return gpt.get_response(message)
 
@@ -19,20 +16,7 @@ def respond(
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.Interface(
-    respond,
-    additional_inputs=[
-        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)",
-        ),
-    ],
-)
+demo = gr.Interface(fn=respond, inputs="textbox", outputs="textbox")
 
 
 if __name__ == "__main__":