tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "+ا",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "1": {
      "content": "+ك",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "2": {
      "content": "ب+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "3": {
      "content": "+هم",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "4": {
      "content": "+ات",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "5": {
      "content": "+ي",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "6": {
      "content": "ل+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "7": {
      "content": "+هما",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "8": {
      "content": "+نا",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "9": {
      "content": "+ن",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "10": {
      "content": "+ها",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "11": {
      "content": "+كما",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "12": {
      "content": "+ة",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "13": {
      "content": "ف+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "14": {
      "content": "+كم",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "15": {
      "content": "+كن",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "16": {
      "content": "+ت",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "17": {
      "content": "[بريد]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "18": {
      "content": "[مستخدم]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "19": {
      "content": "لل+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "20": {
      "content": "ال+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "21": {
      "content": "[رابط]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "22": {
      "content": "س+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "23": {
      "content": "+ان",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "24": {
      "content": "+وا",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "25": {
      "content": "+ه",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "26": {
      "content": "+ون",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "27": {
      "content": "+هن",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "28": {
      "content": "+ين",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "29": {
      "content": "و+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "30": {
      "content": "ك+",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "31": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "33": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "34": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "35": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": false,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": false,
  "extra_special_tokens": {},
  "mask_token": "[MASK]",
  "max_len": 512,
  "max_length": 512,
  "model_max_length": 512,
  "never_split": [
    "+ك",
    "+كما",
    "ك+",
    "+وا",
    "+ين",
    "و+",
    "+كن",
    "+ان",
    "+هم",
    "+ة",
    "[بريد]",
    "لل+",
    "+ي",
    "+ت",
    "+ن",
    "س+",
    "ل+",
    "[مستخدم]",
    "+كم",
    "+ا",
    "ب+",
    "ف+",
    "+نا",
    "+ها",
    "+ون",
    "+هما",
    "ال+",
    "+ه",
    "+هن",
    "+ات",
    "[رابط]"
  ],
  "pad_to_multiple_of": null,
  "pad_token": "[PAD]",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "sep_token": "[SEP]",
  "stride": 0,
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "[UNK]"
}