tokenizer_config.json

{
  "additional_special_tokens": [
    "<special0>",
    "<special1>",
    "<special2>",
    "<special3>",
    "<special4>",
    "<special5>",
    "<special6>",
    "<special7>",
    "<special8>",
    "<special9>"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "cls_token": "</s>",
  "do_lowercase_and_remove_accent": true,
  "id2lang": {
    "0": "ar",
    "1": "bg",
    "10": "th",
    "11": "tr",
    "12": "ur",
    "13": "vi",
    "14": "zh",
    "2": "de",
    "3": "el",
    "4": "en",
    "5": "es",
    "6": "fr",
    "7": "hi",
    "8": "ru",
    "9": "sw"
  },
  "lang2id": {
    "ar": 0,
    "bg": 1,
    "de": 2,
    "el": 3,
    "en": 4,
    "es": 5,
    "fr": 6,
    "hi": 7,
    "ru": 8,
    "sw": 9,
    "th": 10,
    "tr": 11,
    "ur": 12,
    "vi": 13,
    "zh": 14
  },
  "mask_token": "<special1>",
  "model_max_length": 512,
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "tokenizer_class": "XLMTokenizer",
  "unk_token": "<unk>"
}