Update app.py

app.py

@@ -1,7 +1,7 @@
 import os
-import threading
+import threading as Thread
 import time
-import subprocess
+import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
@@ -43,8 +43,8 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 
 model = model.eval()
 
-def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
-    
+@spaces.GPU()
+def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):   
     conversation = []
     for prompt, answer in history:
         conversation.extend([