ModelScope中，使用的是qwen1half-7b-chat，第一次跑通了，这是为什么？

"[ERROR:swift] Authentication token does not exist, failed to access model qwen/Qwen15-7B-Chat which may not exist or may be private. Please login first.
[ERROR:swift] Authentication token does not exist, failed to access model qwen/Qwen15-7B-Chat which may not exist or may be private. Please login first.

Traceback (most recent call last):
File ""c:\users\406\desktop\dev\swift-main\swift\cli\sft.py"", line 5, in
sft_main()
File ""c:\users\406\desktop\dev\swift-main\swift\utils\run_utils.py"", line 27, in x_main
result = llm_x(args, kwargs)
File ""c:\users\406\desktop\dev\swift-main\swift\llm\sft.py"", line 201, in llm_sft
trainer = Seq2SeqTrainer(
File ""c:\users\406\desktop\dev\swift-main\swift\trainers\trainers.py"", line 36, in init
super().init(*args, kwargs)
File ""c:\users\406\desktop\dev\swift-main\swift\trainers\mixin.py"", line 239, in init
super().init(
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\transformers\trainer_seq2seq.py"", line 57, in init
super().init(
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\transformers\trainer.py"", line 514, in init
self._move_model_to_device(model, args.device)
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\transformers\trainer.py"", line 757, in _move_model_to_device
model = model.to(device)
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\torch\nn\modules\module.py"", line 1173, in to
return self._apply(convert)
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\torch\nn\modules\module.py"", line 779, in _apply
module._apply(fn)
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\torch\nn\modules\module.py"", line 779, in _apply
module._apply(fn)
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\torch\nn\modules\module.py"", line 779, in _apply
module._apply(fn)
[Previous line repeated 5 more times]
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\torch\nn\modules\module.py"", line 804, in _apply
param_applied = fn(param)
File ""C:\Users\406\anaconda3\envs\modelscope\lib\site-packages\torch\nn\modules\module.py"", line 1166, in convert
raise NotImplementedError(
NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
ModelScope中，使用的是qwen1half-7b-chat，第一次跑通了，第二次就不行咯，这是为什么？"