uyghur_mpt / tokenizer_config.json
lgessler's picture
Upload 6 files
63572e3
raw
history blame contribute delete
295 Bytes
{
"bos_token": "[CLS]",
"cls_token": "[CLS]",
"do_lower_case": true,
"eos_token": "[SEP]",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}