tokenizer_config.json

{
  "bos_token": "<s>",
  "eos_token": "</s>",
  "sep_token": "</s>",
  "cls_token": "<s>",
  "unk_token": "<unk>",
  "pad_token": "<pad>",
  "mask_token": {
    "content": "<mask>",
    "single_word": false,
    "lstrip": true,
    "rstrip": false,
    "normalized": true,
    "__type": "AddedToken"
  },
  "model_max_length": 512,
  "special_tokens_map_file": null,
  "full_tokenizer_file": null,
  "do_lower_case": false,
  "tokenizer_class": "XLMRobertaTokenizer",
  "is_split_into_words": true,
  "use_fast": true
}