Update app.py

app.py

@@ -1,4 +1,5 @@
 from threading import Thread
+import spaces
 
 import torch
 import gradio as gr
@@ -12,6 +13,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16
 assistant_model = AutoModelForCausalLM.from_pretrained(assistant_id).to(device=model.device, dtype=torch.bfloat16)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
+@spaces.GPU
 def run_generation(user_text, use_assistant, temperature, max_new_tokens):
     if temperature < 0.1:
         do_sample = False