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": 60,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Metaspace",
    "replacement": "▁",
    "prepend_scheme": "first",
    "split": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 1
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<s>": {
        "id": "<s>",
        "ids": [
          1
        ],
        "tokens": [
          "<s>"
        ]
      }
    }
  },
  "decoder": {
    "type": "Sequence",
    "decoders": [
      {
        "type": "Replace",
        "pattern": {
          "String": "▁"
        },
        "content": " "
      },
      {
        "type": "ByteFallback"
      },
      {
        "type": "Fuse"
      },
      {
        "type": "Strip",
        "content": " ",
        "start": 1,
        "stop": 0
      }
    ]
  },
  "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": {
      "<unk>": 0,
      "<s>": 1,
      "</s>": 2,
      "#": 3,
      "(": 4,
      ")": 5,
      "+": 6,
      "-": 7,
      "/": 8,
      "1": 9,
      "2": 10,
      "3": 11,
      "4": 12,
      "5": 13,
      "=": 14,
      "@": 15,
      "B": 16,
      "C": 17,
      "F": 18,
      "H": 19,
      "I": 20,
      "N": 21,
      "O": 22,
      "S": 23,
      "[": 24,
      "\\": 25,
      "]": 26,
      "c": 27,
      "l": 28,
      "n": 29,
      "o": 30,
      "r": 31,
      "s": 32,
      "▁": 33,
      "cc": 34,
      "CC": 35,
      "O)": 36,
      "c1": 37,
      "=O)": 38,
      "(=O)": 39,
      "(C": 40,
      "c2": 41,
      "H]": 42,
      "C@": 43,
      "[C@": 44,
      "c1cc": 45,
      "c(": 46,
      "▁C": 47,
      "C(=O)": 48,
      "(C)": 49,
      "2)": 50,
      "[C@H]": 51,
      "[C@@": 52,
      "c3": 53,
      "c2cc": 54,
      "[C@@H]": 55,
      ")cc": 56,
      "NC(=O)": 57,
      "CCC": 58,
      "(=O)N": 59
    },
    "merges": [
      [
        "c",
        "c"
      ],
      [
        "C",
        "C"
      ],
      [
        "O",
        ")"
      ],
      [
        "c",
        "1"
      ],
      [
        "=",
        "O)"
      ],
      [
        "(",
        "=O)"
      ],
      [
        "(",
        "C"
      ],
      [
        "c",
        "2"
      ],
      [
        "H",
        "]"
      ],
      [
        "C",
        "@"
      ],
      [
        "[",
        "C@"
      ],
      [
        "c1",
        "cc"
      ],
      [
        "c",
        "("
      ],
      [
        "▁",
        "C"
      ],
      [
        "C",
        "(=O)"
      ],
      [
        "(C",
        ")"
      ],
      [
        "2",
        ")"
      ],
      [
        "[C@",
        "H]"
      ],
      [
        "[C@",
        "@"
      ],
      [
        "c",
        "3"
      ],
      [
        "c2",
        "cc"
      ],
      [
        "[C@@",
        "H]"
      ],
      [
        ")",
        "cc"
      ],
      [
        "N",
        "C(=O)"
      ],
      [
        "CC",
        "C"
      ],
      [
        "(=O)",
        "N"
      ]
    ]
  }
}