indo-sentence-bert-base / tokenizer_config.json
Firqa Aqila Noor A
Upload tokenizer_config.json
8f8f456
raw
history blame
527 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"name_or_path": "indobenchmark/indobert-base-p1",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--indobenchmark--indobert-base-p1/snapshots/c2cd0b51ddce6580eb35263b39b0a1e5fb0a39e2/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}