gector-bert-es / tokenizer_config.json
Imperatore's picture
gector-bert-es: first public release (CC BY 4.0, base BETO)
571b34f verified
Raw History Blame Contribute Delete
405 Bytes
{
"backend": "tokenizers",
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"is_local": false,
"local_files_only": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}