indo-sentence-bert-base / tokenizer_config.json
firqaaa's picture
Upload tokenizer_config.json
2c4e2db
raw
history blame contribute delete
551 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/transformers/b515a756d9ddf12a7a391ea596c488ac805f0576790934e590ce250a3e4ff056.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}