kobigbird-bert-base / tokenizer_config.json
{
"do_lower_case": false,
"unk_token": "[UNK]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"tokenize_chinese_chars": true,
"strip_accents": null,
"do_basic_tokenize": true,
"never_split": null,
"bos_token": "<s>",
"eos_token": "</s>",
"model_max_length": 4096,
"tokenizer_class": "BertTokenizer"
}