VAC-BERT / tokenizer_config.json
Vacaspati's picture
tokenizer for Vac-BERT uploaded
a98e542 verified
raw
history blame contribute delete
296 Bytes
{
"do_lower_case": false,
"unk_token": "[UNK]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"model_max_length": 512,
"tokenizer_class": "BertTokenizer",
"clean_text": true,
"handle_chinese_chars": false,
"strip_accents": null
}