Update app.py

app.py

@@ -18,6 +18,7 @@ import gradio as gr
 from controller import Controller
 
 # Loading Model
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,                  # Load model weights in 4-bit format
     bnb_4bit_compute_type=torch.float16 # To avoid slow inference as input type into Linear4bit is torch.float16