tcr-bert-finetuned-tchard / tokenizer_config.json
yiminghuang47's picture
Training in progress, step 500
e713c6a
raw
history blame
425 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "*",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": ".",
"model_max_len": 45,
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "$",
"padding_side": "right",
"sep_token": "|",
"strip_accents": null,
"tokenize_chinese_chars": false,
"tokenizer_class": "BertTokenizer",
"unk_token": "?"
}