Update app.py

app.py

@@ -5,7 +5,7 @@ from threading import Thread
 from typing import Iterator
 
 import gradio as gr
-import spaces
+# import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
@@ -19,7 +19,7 @@ if torch.cuda.is_available():
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 
-@spaces.GPU
+# @spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],