tokenizer_config.json

{
    "do_lowercase_and_remove_accent": true,
    "id2lang": {
        "0": "ar",
        "1": "bg",
        "2": "de",
        "3": "el",
        "4": "en",
        "5": "es",
        "6": "fr",
        "7": "hi",
        "8": "ru",
        "9": "sw",
        "10": "th",
        "11": "tr",
        "12": "ur",
        "13": "vi",
        "14": "zh"
    },
    "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
    },
    "vocab_file": "C:\\Users\\yujun\\.paddlenlp\\models\\xlm-mlm-tlm-xnli15-1024\\vocab.json",
    "merges_file": "C:\\Users\\yujun\\.paddlenlp\\models\\xlm-mlm-tlm-xnli15-1024\\merges.txt",
    "init_class": "XLMTokenizer"
}