arabert-gec-v2-3 / tokenizer_config.json
s3h's picture
Upload tokenizer_config.json
7b496c4
{"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, "do_basic_tokenize": true, "never_split": ["[بريد]", "[مستخدم]", "[رابط]"], "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-base-arabertv02", "return_tensors": "tf", "tokenizer_class": "BertTokenizer"}