tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<unk>",
      "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": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "mod",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "=",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 6,
      "content": "0",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 7,
      "content": "1",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 8,
      "content": "2",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 9,
      "content": "3",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 10,
      "content": "4",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 11,
      "content": "5",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 12,
      "content": "6",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 13,
      "content": "7",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 14,
      "content": "8",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 15,
      "content": "9",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true,
    "use_regex": true
  },
  "post_processor": null,
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<unk>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<unk>": 0,
      "<s>": 1,
      "</s>": 2,
      "<pad>": 3,
      "mod": 4,
      "=": 5,
      "0": 6,
      "1": 7,
      "2": 8,
      "3": 9,
      "4": 10,
      "5": 11,
      "6": 12,
      "7": 13,
      "8": 14,
      "9": 15,
      "Ġ": 16,
      "Ġ0": 17,
      "Ġ1": 18,
      "Ġ2": 19,
      "Ġ3": 20,
      "Ġ4": 21,
      "Ġ5": 22,
      "Ġ6": 23,
      "Ġ7": 24,
      "Ġ8": 25,
      "Ġ9": 26
    },
    "merges": [
      [
        "Ġ",
        "0"
      ],
      [
        "Ġ",
        "1"
      ],
      [
        "Ġ",
        "2"
      ],
      [
        "Ġ",
        "3"
      ],
      [
        "Ġ",
        "4"
      ],
      [
        "Ġ",
        "5"
      ],
      [
        "Ġ",
        "6"
      ],
      [
        "Ġ",
        "7"
      ],
      [
        "Ġ",
        "8"
      ],
      [
        "Ġ",
        "9"
      ]
    ]
  }
}