indobert-large-p2-finetuned-squad / tokenizer_config.json
ageng-anugrah's picture
First version
6a5155c
{
"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-p2/snapshots/4b280c3bfcc1ed2d6b4589be5c876076b7d73568/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}