tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 33,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 34,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 35,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 36,
      "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,
      "1": 6,
      "2": 7,
      "3": 8,
      "4": 9,
      "5": 10,
      "6": 11,
      "=": 12,
      "@": 13,
      "B": 14,
      "C": 15,
      "F": 16,
      "H": 17,
      "I": 18,
      "N": 19,
      "O": 20,
      "P": 21,
      "S": 22,
      "[": 23,
      "\\": 24,
      "]": 25,
      "c": 26,
      "i": 27,
      "l": 28,
      "n": 29,
      "o": 30,
      "r": 31,
      "s": 32
    },
    "merges": []
  }
}