bert的一系列资料-蒲公英云

bert的一系列资料

1.bert-as-service

https://github.com/hanxiao/bert-as-service

2.参考文献

3.预训练模型下载链接：https://linux.ctolib.com/article/wiki/99669

The links to the models are here (right-click, ‘Save link as…’ on the name):

BERT-Base, Uncased: 12-layer, 768-hidden, 12-heads, 110M parameters
BERT-Large, Uncased: 24-layer, 1024-hidden, 16-heads, 340M parameters
BERT-Base, Cased: 12-layer, 768-hidden, 12-heads , 110M parameters
BERT-Large, Cased: 24-layer, 1024-hidden, 16-heads, 340M parameters
BERT-Base, Multilingual Cased (New, recommended): 104 languages, 12-layer, 768-hidden, 12-heads, 110M parameters
BERT-Base, Multilingual Uncased (Orig, not recommended) (Not recommended, use Multilingual Cased instead): 102 languages, 12-layer, 768-hidden, 12-heads, 110M parameters
BERT-Base, Chinese: Chinese Simplified and Traditional, 12-layer, 768-hidden, 12-heads, 110M parameters

我们发布了论文中的BERT-Base和BERT-Large模型。

Uncased表示在WordPiece tokenization之前文本已经变成小写了，例如，John Smith becomes john smith。Uncased模型也去掉了所有重音标志。

Cased表示保留了真实的大小写和重音标记。通常，除非你已经知道大小写信息对你的任务来说很重要（例如，命名实体识别或词性标记），否则Uncased模型会更好。

Each .zip file contains three items:

A TensorFlow checkpoint (bert_model.ckpt) containing the pre-trained weights (which is actually 3 files).
A vocab file (vocab.txt) to map WordPiece to word id.
A config file (bert_config.json) which specifies the hyperparameters of the model.