DarijaBERT / tokenizer_config.json
Kamel's picture
add tokenizer
8b5b5b2
raw
history blame
400 Bytes
{"do_lower_case": true, "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": "/content/drive/MyDrive/Doctorat/DarijaBERT/Models/DarijaBert_v1.0/epoch40", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}