kob400 / tokenizer_config.json
kimhee96
commit from
312e958
raw
history blame
323 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, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "monologg/kobert", "do_basic_tokenize": true, "never_split": null}