U4RASD/NeoAraBERT

1{2  "added_tokens_decoder": {3    "0": {4      "content": "[PAD]",5      "lstrip": false,6      "normalized": false,7      "rstrip": false,8      "single_word": false,9      "special": true10    },11    "1": {12      "content": "[UNK]",13      "lstrip": false,14      "normalized": false,15      "rstrip": false,16      "single_word": false,17      "special": true18    },19    "2": {20      "content": "[CLS]",21      "lstrip": false,22      "normalized": false,23      "rstrip": false,24      "single_word": false,25      "special": true26    },27    "3": {28      "content": "[SEP]",29      "lstrip": false,30      "normalized": false,31      "rstrip": false,32      "single_word": false,33      "special": true34    },35    "4": {36      "content": "[MASK]",37      "lstrip": false,38      "normalized": false,39      "rstrip": false,40      "single_word": false,41      "special": true42    },43    "5": {44      "content": "[+]",45      "lstrip": false,46      "normalized": false,47      "rstrip": false,48      "single_word": false,49      "special": true50    }51  },52  "additional_special_tokens": [53    "[+]"54  ],55  "clean_up_tokenization_spaces": false,56  "cls_token": "[CLS]",57  "do_lower_case": false,58  "extra_special_tokens": {},59  "mask_token": "[MASK]",60  "model_max_length": 1000000000000000019884624838656,61  "pad_token": "[PAD]",62  "sep_token": "[SEP]",63  "strip_accents": null,64  "tokenize_chinese_chars": true,65  "tokenizer_class": "ArabicMorphTokenizer",66  "trust_remote_code": true,67  "unk_token": "[UNK]",68  "auto_map": {69    "AutoTokenizer": ["tokenizer.ArabicMorphTokenizer", null]70  },71  "apply_stemming": true72}73