polite_bert / tokenizer_config.json
dmgcsilva's picture
Upload tokenizer
b336e87
raw
history blame
529 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "experiments/polite_bert/polite_bert_v1/train/final",
"never_split": null,
"pad_token": "[PAD]",
"padding": true,
"return_attention_mask": true,
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation": false,
"unk_token": "[UNK]",
"use_fast": false
}