IndoBERT-Lite-Large-QA / tokenizer_config.json
Rifky's picture
Training in progress epoch 0
fc30ba2
raw
history blame contribute delete
594 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "indobenchmark/indobert-lite-large-p2",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--indobenchmark--indobert-lite-large-p2/snapshots/14818646c71e898fe71351d12a1dc9fe1bf39ba5/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}