reinvent_42M_64/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 64,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 65,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 66,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 67,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "\\(|\\)"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": {
    "type": "BPEDecoder",
    "suffix": "</w>"
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "#": 0,
      "%": 1,
      "(": 2,
      ")": 3,
      "+": 4,
      "-": 5,
      "/": 6,
      "0": 7,
      "1": 8,
      "2": 9,
      "3": 10,
      "4": 11,
      "5": 12,
      "6": 13,
      "7": 14,
      "8": 15,
      "9": 16,
      "=": 17,
      "@": 18,
      "B": 19,
      "C": 20,
      "F": 21,
      "H": 22,
      "I": 23,
      "N": 24,
      "O": 25,
      "P": 26,
      "S": 27,
      "[": 28,
      "\\": 29,
      "]": 30,
      "c": 31,
      "i": 32,
      "l": 33,
      "n": 34,
      "o": 35,
      "r": 36,
      "s": 37,
      "cc": 38,
      "CC": 39,
      "c1": 40,
      "=O": 41,
      "c2": 42,
      "H]": 43,
      "[C": 44,
      "[C@": 45,
      "c1cc": 46,
      "[C@@": 47,
      "c3": 48,
      "c2cc": 49,
      "[C@H]": 50,
      "[C@@H]": 51,
      "NC": 52,
      "c1ccc": 53,
      "CCC": 54,
      "CO": 55,
      "cc1": 56,
      "=C": 57,
      "c1cccc": 58,
      "n1": 59,
      "N1": 60,
      "nc": 61,
      "c2cccc": 62,
      "OC": 63
    },
    "merges": [
      [
        "c",
        "c"
      ],
      [
        "C",
        "C"
      ],
      [
        "c",
        "1"
      ],
      [
        "=",
        "O"
      ],
      [
        "c",
        "2"
      ],
      [
        "H",
        "]"
      ],
      [
        "[",
        "C"
      ],
      [
        "[C",
        "@"
      ],
      [
        "c1",
        "cc"
      ],
      [
        "[C@",
        "@"
      ],
      [
        "c",
        "3"
      ],
      [
        "c2",
        "cc"
      ],
      [
        "[C@",
        "H]"
      ],
      [
        "[C@@",
        "H]"
      ],
      [
        "N",
        "C"
      ],
      [
        "c1cc",
        "c"
      ],
      [
        "CC",
        "C"
      ],
      [
        "C",
        "O"
      ],
      [
        "cc",
        "1"
      ],
      [
        "=",
        "C"
      ],
      [
        "c1cc",
        "cc"
      ],
      [
        "n",
        "1"
      ],
      [
        "N",
        "1"
      ],
      [
        "n",
        "c"
      ],
      [
        "c2cc",
        "cc"
      ],
      [
        "O",
        "C"
      ]
    ]
  }
}