turkic-cyrillic-classifier / tokenizer_config.json
tatiana-merz's picture
Training in progress, step 500
06f541b
raw
history blame
310 Bytes
{
"cls_token": "[CLS]",
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}