Update app.py

app.py

@@ -15,7 +15,9 @@ use_triton = False
 
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
-device="cuda" if torch.cuda.is_available() else "cpu"):
+device=("cuda" if torch.cuda.is_available() else "cpu")
+#device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+#device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
 
 model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
         use_safetensors=True,