Update app.py

app.py

@@ -6,7 +6,8 @@ from threading import Thread
 tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
 model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
 model = model.to('cuda:0')
-
+cfg = get_cfg()
+cfg.MODEL.DEVICE = 'cpu'
 class StopOnTokens(StoppingCriteria):
     def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
         stop_ids = [29, 0]