ios/tokenizer/tokenizer_config.json

{
  "add_prefix_space": true,
  "added_tokens_decoder": {
    "0": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128000": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128001": {
      "content": "[SEP_STRUCT]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128002": {
      "content": "[SEP_TEXT]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128003": {
      "content": "[P]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128004": {
      "content": "[C]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128005": {
      "content": "[E]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128006": {
      "content": "[R]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128007": {
      "content": "[L]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128008": {
      "content": "[EXAMPLE]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128009": {
      "content": "[OUTPUT]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "128010": {
      "content": "[DESCRIPTION]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "[SEP_STRUCT]",
    "[SEP_TEXT]",
    "[P]",
    "[C]",
    "[E]",
    "[R]",
    "[L]",
    "[EXAMPLE]",
    "[OUTPUT]",
    "[DESCRIPTION]"
  ],
  "backend": "tokenizers",
  "bos_token": "[CLS]",
  "clean_up_tokenization_spaces": false,
  "cls_token": "[CLS]",
  "do_lower_case": false,
  "eos_token": "[SEP]",
  "extra_special_tokens": {},
  "is_local": false,
  "local_files_only": false,
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "sp_model_kwargs": {},
  "split_by_punct": false,
  "tokenizer_class": "XLMRobertaTokenizer",
  "unk_id": 3,
  "unk_token": "[UNK]",
  "vocab_type": "spm"
}