mbert-sindhi-tokenizer / tokenizer_config.json
Kashif786's picture
Add 20k Sindhi unigram tokens to Mbert for thesis research
781e397 verified
raw
history blame contribute delete
323 Bytes
{
"backend": "tokenizers",
"cls_token": "[CLS]",
"do_lower_case": false,
"is_local": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}