ARBERTv2 / tokenizer_config.json
elmadany
commit from elmadany
7f1e104
raw
history blame contribute delete
485 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "/project/6007993/DataBank/models_from_scratch/ARBERTv2/700K_v3-128/pytorch",
"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]"
}