BERT-NER-Classifier / tokenizer_config.json
phanerozoic's picture
Update tokenizer_config.json
ebae515 verified
raw
history blame
464 Bytes
{
"do_lower_case": true,
"unk_token": "[UNK]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"model_max_length": 512,
"tokenize_chinese_chars": true,
"strip_accents": null,
"do_basic_tokenize": true,
"clean_up_tokenization_spaces": false,
"tokenizer_class": "BertTokenizer",
"special_tokens_map_file": null,
"max_len": 512,
"max_len_single_sentence": 510,
"max_len_sentences_pair": 506
}