| {"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": ["+ู", "+ูู ุง", "+ูู", "+ุช", "+ูุง", "ู+", "+ูู ุง", "+ู", "ุจ+", "+ู", "ูู+", "ู+", "[ุจุฑูุฏ]", "ู+", "+ูุง", "+ุงู", "[ู ุณุชุฎุฏู ]", "+ูุง", "[ุฑุงุจุท]", "+ูู", "ุณ+", "+ูู ", "+ูู", "ุงู+", "+ุฉ", "+ูู", "ู+", "+ุง", "+ูู ", "+ุงุช", "+ู"], "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-base-arabertv02", "tokenizer_class": "BertTokenizer"} |