nb-bert-base / tokenizer_config.json
versae's picture
First version of the Nasjonalbiblioteket BERT-based model
83e1255
raw
history blame
363 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/disk4/folder1/working/checkpoints/huggingface/native_pytorch/step1_1/", "do_basic_tokenize": true, "never_split": null}