bge-large-en / tokenizer_config.json
freaksamael's picture
Update tokenizer_config.json
f52c5d3
raw
history blame
368 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 2048,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": false,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}