IndoBERT-SQuAD / tokenizer_config.json
esakrissa's picture
Training in progress, epoch 3
47034de
raw history blame
No virus
580 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "indolem/indobert-base-uncased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--indolem--indobert-base-uncased/snapshots/b6663c19a819c04798e7a93d681f9bc34ed57b4a/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}