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": "<unk>",
      "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": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<m>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "</m>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "Split",
        "pattern": {
          "Regex": "(<pad>|<unk>|<s>|</s>|<m>|</m>)"
        },
        "behavior": "Isolated",
        "invert": false
      },
      {
        "type": "Split",
        "pattern": {
          "Regex": "(?!.*>)"
        },
        "behavior": "Isolated",
        "invert": false
      }
    ]
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "</s>": {
        "id": "</s>",
        "ids": [
          3
        ],
        "tokens": [
          "</s>"
        ]
      },
      "<s>": {
        "id": "<s>",
        "ids": [
          2
        ],
        "tokens": [
          "<s>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<unk>": 1,
      "<s>": 2,
      "</s>": 3,
      "<m>": 4,
      "</m>": 5,
      "L": 6,
      "A": 7,
      "G": 8,
      "V": 9,
      "E": 10,
      "S": 11,
      "I": 12,
      "K": 13,
      "R": 14,
      "D": 15,
      "T": 16,
      "P": 17,
      "F": 18,
      "N": 19,
      "Q": 20,
      "Y": 21,
      "M": 22,
      "H": 23,
      "C": 24,
      "W": 25,
      "X": 26,
      "B": 27,
      "Z": 28,
      "U": 29,
      "O": 30
    },
    "unk_token": "<unk>"
  }
}