Update app.py

app.py

@@ -10,12 +10,14 @@ from tqdm import tqdm
 from dotenv import load_dotenv
 from pydantic import BaseModel
 import asyncio
+from huggingface_hub import login
 
 load_dotenv()
 os.system("pip install --upgrade llama-cpp-python")
 
 app = FastAPI()
 HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
+login(token=HUGGINGFACE_TOKEN)
 
 global_data = {
     'model_configs': [
@@ -123,6 +125,7 @@ iface = gr.Interface(
     live=False
 )
 
+@spaces.GPU()
 if __name__ == "__main__":
     port = int(os.environ.get("PORT", 7860))
     iface.launch(server_port=port)