hubertusz-medium-wiki / tokenizer_config.json
Tamás Ficsor
add tokenizer
2519a5b
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"full_tokenizer_file": null,
"mask_token": "[MASK]",
"name_or_path": "datasets/hubert-medium-plus-100k-checkpoint-last/",
"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]"
}