indobert-large-p1-v1 / tokenizer_config.json
ageng-anugrah's picture
Upload tokenizer
e4f5d40 verified
raw
history blame contribute delete
531 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--indobenchmark--indobert-large-p1/snapshots/ee2669aee95421008ad3833c3866c57a006e662d/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}