deberta-base-chinese-erlangshen-upos / tokenizer_config.json
KoichiYasuoka's picture
initial release
7bd6465
raw history blame
No virus
330 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizerFast",
"unk_token": "[UNK]"
}