Update app.py

app.py

@@ -4,6 +4,7 @@ import sys
 import html
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
 from threading import Thread
+import spaces
 
 model_name_or_path = 'TencentARC/Mistral_Pro_8B_v0.1'
 
@@ -46,6 +47,7 @@ def convert_history(chat_history, max_input_length=1024):
         history_text = "<|assistant|>\n"
     return history_text
 
+@spaces.GPU
 @torch.inference_mode()
 def instruct(instruction, max_token_output=1024):
     input_text = instruction