scandi-nli-large / tokenizer_config.json
saattrupdan's picture
Update tokenizer_config.json
a211cc6
raw history blame
No virus
405 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"name_or_path": "NbAiLab/nb-bert-large",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]",
"model_max_length": 512
}