Huggingface的变形金刚管道

Question

我正在尝试从拥抱面孔

https://github.com/huggingface/transformers#installation

在系统上运行时，我得到不同的结果

>>> import transformers
>>> transformers.__version__
'2.8.0'


I am running on Python 3.7.6 


>>> from transformers import pipeline
>>> nlp = pipeline('sentiment-analysis')
Downloading: 100%|███████████████████████████████████████████████████████| 230/230 [00:00<00:00, 77.3kB/s]
2020-04-08 18:04:33.862653: W tensorflow/python/util/util.cc:319] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
2020-04-08 18:04:33.931454: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa52e6b7be0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-04-08 18:04:33.931486: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
>>> nlp('We are very happy to include pipeline into the transformers repository.')
[{'label': 'NEGATIVE', 'score': 0.94570833}]
>>> 

有什么我可以研究的吗？