Update app.py

app.py

@@ -1,6 +1,6 @@
 import os
 import time
-# import spaces
+import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, BitsAndBytesConfig
 import gradio as gr
@@ -46,7 +46,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto",
     quantization_config=quantization_config)
 
-# @spaces.GPU()
+@spaces.GPU()
 def stream_chat(
     message: str, 
     history: list,