greek-media-bert-base-uncased / tokenizer_config.json
d1mitriz
First version of the your-model-name model and tokenizer.
4f4f462
raw
history blame contribute delete
461 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "greek-media-bert-base-uncased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}