Update app.py

app.py

@@ -30,8 +30,9 @@ streamer = TextStreamer(tokenizer)
 model = AutoModelForCausalLM.from_pretrained(model, trust_remote_code=True, token = access_token, device_map="auto", offload_folder="offload/")
 model = PeftModel.from_pretrained(model, peft_model,  device_map="auto", offload_folder="offload/")
 
-device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+#device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
 #device = 'cuda:0'
+#device = 'cpu'
 model = model.to(device)
 model = model.eval()