ConGen-Multilingual-DistilBERT / tokenizer_config.json
kornwtp's picture
Initial commit
73209cf
raw
history blame
No virus
338 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": "pretrianed_models/distilbert-base-multilingual-cased", "tokenizer_class": "DistilBertTokenizer"}