BIG-29000 / tokenizer_config.json
jjonhwa's picture
Upload tokenizer
eb39037
raw
history blame contribute delete
413 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"eos_token": "</s>",
"mask_token": "[MASK]",
"model_max_length": 4096,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}