tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<mask>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "Ever:",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    {
      "id": 6,
      "content": "Small:",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    }
  ],
  "normalizer": {
    "type": "Replace",
    "pattern": {
      "String": " "
    },
    "content": "▁"
  },
  "pre_tokenizer": null,
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": {
    "type": "Sequence",
    "decoders": [
      {
        "type": "Replace",
        "pattern": {
          "String": "▁"
        },
        "content": " "
      },
      {
        "type": "ByteFallback"
      },
      {
        "type": "Fuse"
      }
    ]
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<unk>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": true,
    "byte_fallback": true,
    "ignore_merges": false,
    "vocab": {
      "<pad>": 0,
      "</s>": 1,
      "<s>": 2,
      "<unk>": 3,
      "<mask>": 4,
      "Ever:": 5,
      "Small:": 6,
      "▁": 7,
      "a": 8,
      "i": 9,
      "e": 10,
      "n": 11,
      "l": 12,
      "o": 13,
      "r": 14,
      "y": 15,
      "m": 16,
      "t": 17,
      "u": 18,
      "c": 19,
      "s": 20,
      "p": 21,
      "k": 22,
      "d": 23,
      "j": 24,
      "z": 25,
      "g": 26,
      "b": 27,
      "h": 28,
      "v": 29,
      "A": 30,
      "f": 31,
      "q": 32,
      "x": 33,
      "I": 34,
      "Y": 35,
      "E": 36,
      "D": 37,
      "L": 38,
      "M": 39,
      "N": 40,
      "O": 41,
      "w": 42,
      "F": 43,
      "P": 44,
      "U": 45,
      "W": 46,
      "X": 47,
      "B": 48,
      "G": 49,
      "J": 50,
      "Q": 51,
      "S": 52,
      "T": 53
    },
    "merges": []
  }
}