ofa-cn-base-muge-v2 / tokenizer_config.json
YeungNLP's picture
Upload 7 files
ede6c52
raw
history blame contribute delete
398 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"do_basic_tokenize": true,
"do_lower_case": true,
"eos_token": "</s>",
"mask_token": "<mask>",
"name_or_path": "",
"never_split": null,
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "<unk>"
}