NonToxicCivilBert / tokenizer_config.json
Ashokajou51's picture
Upload tokenizer
a4a1288
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 256,
"model_max_length": 512,
"name_or_path": "/content/CB/civilBertV2",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]",
"use_fast": true
}