24 lines
565 B
JSON
24 lines
565 B
JSON
{
|
|
"backend": "tokenizers",
|
|
"cls_token": "[CLS]",
|
|
"do_basic_tokenize": true,
|
|
"do_lower_case": true,
|
|
"is_local": false,
|
|
"mask_token": "[MASK]",
|
|
"max_length": 128,
|
|
"model_max_length": 256,
|
|
"never_split": null,
|
|
"pad_to_multiple_of": null,
|
|
"pad_token": "[PAD]",
|
|
"pad_token_type_id": 0,
|
|
"padding_side": "right",
|
|
"sep_token": "[SEP]",
|
|
"stride": 0,
|
|
"strip_accents": null,
|
|
"tokenize_chinese_chars": true,
|
|
"tokenizer_class": "BertTokenizer",
|
|
"truncation_side": "right",
|
|
"truncation_strategy": "longest_first",
|
|
"unk_token": "[UNK]"
|
|
}
|