chinese-lm-30m / tokenizer_config.json
BravePaul's picture
first cmt
392ca18
raw
history blame contribute delete
No virus
536 Bytes
{
"bos_token": "<s>",
"cls_token": "<cls>",
"do_lower_case": true,
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "<sep>",
"special_tokens_map_file": "/home/bravepaul/.cache/huggingface/hub/models--MLRush--bert-tiny-chinese-tokenize/snapshots/21e5875c479d131f7cabc77e1ee7a9814ad44e04/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "<unk>"
}