roberta-large-korean-ud-goeswith / tokenizer_config.json
KoichiYasuoka's picture
initial release
45d76b3
raw
history blame contribute delete
379 Bytes
{
"bos_token": "[CLS]",
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"eos_token": "[SEP]",
"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]"
}