bodo-bert-mlm-base-article / tokenizer_config.json
Sanjib Narzary
Bodo BERT Base with All Article of News and General Corpus
2d155ba
raw
history blame
No virus
519 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "/home/sn/pretrained_models/huggingface_pretrained/brx-bert-base-mlm-scratch/pretrained-brx-bert-base-article",
"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]"
}