tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[cls]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 255,
      "content": "[bos]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 256,
      "content": "[pad]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 257,
      "content": "[eos]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 258,
      "content": "[sep]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 259,
      "content": "[unk]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "WhitespaceSplit"
      },
      {
        "type": "Split",
        "pattern": {
          "Regex": "(\\[[a-z]+]|\\[[A-Z][a-z]?|Br?|Cl?|N|O|S|P|F|I|H[2-4]?|\\[|\\]|,|;|\\(|\\)|\\.|=|\\#|-|\\+|\\\\|/|:|~|@|\\?|>|\\*|\\$|%|(?<=%)[0-9]{2}|(?<=,)[0-9]{2}(?=\\))|(?<=\\()[0-9]{2}(?=,)|(?<=:)[0-9]{2}(?=\\])|[0-9]|\\|)"
        },
        "behavior": "Isolated",
        "invert": false
      }
    ]
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "[cls]": 0,
      "[H": 1,
      "[He": 2,
      "[Li": 3,
      "[Be": 4,
      "[B": 5,
      "[C": 6,
      "[N": 7,
      "[O": 8,
      "[F": 9,
      "[Ne": 10,
      "[Na": 11,
      "[Mg": 12,
      "[Al": 13,
      "[Si": 14,
      "[P": 15,
      "[S": 16,
      "[Cl": 17,
      "[Ar": 18,
      "[K": 19,
      "[Ca": 20,
      "[Sc": 21,
      "[Ti": 22,
      "[V": 23,
      "[Cr": 24,
      "[Mn": 25,
      "[Fe": 26,
      "[Co": 27,
      "[Ni": 28,
      "[Cu": 29,
      "[Zn": 30,
      "[Ga": 31,
      "[Ge": 32,
      "[As": 33,
      "[Se": 34,
      "[Br": 35,
      "[Kr": 36,
      "[Rb": 37,
      "[Sr": 38,
      "[Y": 39,
      "[Zr": 40,
      "[Nb": 41,
      "[Mo": 42,
      "[Tc": 43,
      "[Ru": 44,
      "[Rh": 45,
      "[Pd": 46,
      "[Ag": 47,
      "[Cd": 48,
      "[In": 49,
      "[Sn": 50,
      "[Sb": 51,
      "[Te": 52,
      "[I": 53,
      "[Xe": 54,
      "[Cs": 55,
      "[Ba": 56,
      "[La": 57,
      "[Ce": 58,
      "[Pr": 59,
      "[Nd": 60,
      "[Pm": 61,
      "[Sm": 62,
      "[Eu": 63,
      "[Gd": 64,
      "[Tb": 65,
      "[Dy": 66,
      "[Ho": 67,
      "[Er": 68,
      "[Tm": 69,
      "[Yb": 70,
      "[Lu": 71,
      "[Hf": 72,
      "[Ta": 73,
      "[W": 74,
      "[Re": 75,
      "[Os": 76,
      "[Ir": 77,
      "[Pt": 78,
      "[Au": 79,
      "[Hg": 80,
      "[Tl": 81,
      "[Pb": 82,
      "[Bi": 83,
      "[Po": 84,
      "[At": 85,
      "[Rn": 86,
      "[Fr": 87,
      "[Ra": 88,
      "[Ac": 89,
      "[Th": 90,
      "[Pa": 91,
      "[U": 92,
      "[Np": 93,
      "[Pu": 94,
      "[Am": 95,
      "[Cm": 96,
      "[Bk": 97,
      "[Cf": 98,
      "[Es": 99,
      "[Fm": 100,
      "[Md": 101,
      "[No": 102,
      "[Lr": 103,
      "[Rf": 104,
      "[Db": 105,
      "[Sg": 106,
      "[Bh": 107,
      "[Hs": 108,
      "[Mt": 109,
      "[Ds": 110,
      "[Rg": 111,
      "[Cn": 112,
      "[Nh": 113,
      "[Fl": 114,
      "[Mc": 115,
      "[Lv": 116,
      "[Ts": 117,
      "[Og": 118,
      "C": 119,
      "Cl": 120,
      "B": 121,
      "Br": 122,
      "N": 123,
      "O": 124,
      "S": 125,
      "P": 126,
      "F": 127,
      "I": 128,
      "H": 129,
      "H2": 130,
      "H3": 131,
      "H4": 132,
      "[": 133,
      "]": 134,
      ":": 135,
      "=": 136,
      "#": 137,
      "$": 138,
      "\\": 139,
      "/": 140,
      "(": 141,
      ")": 142,
      ".": 143,
      "[prod]": 144,
      "[reac]": 145,
      "[mech]": 146,
      "+": 147,
      "-": 148,
      "@": 149,
      "*": 150,
      "0": 151,
      "1": 152,
      "2": 153,
      "3": 154,
      "4": 155,
      "5": 156,
      "6": 157,
      "7": 158,
      "8": 159,
      "9": 160,
      "10": 161,
      "11": 162,
      "12": 163,
      "13": 164,
      "14": 165,
      "15": 166,
      "16": 167,
      "17": 168,
      "18": 169,
      "19": 170,
      "20": 171,
      "21": 172,
      "22": 173,
      "23": 174,
      "24": 175,
      "25": 176,
      "26": 177,
      "27": 178,
      "28": 179,
      "29": 180,
      "30": 181,
      "31": 182,
      "32": 183,
      "33": 184,
      "34": 185,
      "35": 186,
      "36": 187,
      "37": 188,
      "38": 189,
      "39": 190,
      "40": 191,
      "41": 192,
      "42": 193,
      "43": 194,
      "44": 195,
      "45": 196,
      "46": 197,
      "47": 198,
      "48": 199,
      "49": 200,
      "50": 201,
      "51": 202,
      "52": 203,
      "53": 204,
      "54": 205,
      "55": 206,
      "56": 207,
      "57": 208,
      "58": 209,
      "59": 210,
      "60": 211,
      "61": 212,
      "62": 213,
      "63": 214,
      "64": 215,
      "65": 216,
      "66": 217,
      "67": 218,
      "68": 219,
      "69": 220,
      "70": 221,
      "71": 222,
      "72": 223,
      "73": 224,
      "74": 225,
      "75": 226,
      "76": 227,
      "77": 228,
      "78": 229,
      "79": 230,
      "80": 231,
      "81": 232,
      "82": 233,
      "83": 234,
      "84": 235,
      "85": 236,
      "86": 237,
      "87": 238,
      "88": 239,
      "89": 240,
      "90": 241,
      "91": 242,
      "92": 243,
      "93": 244,
      "94": 245,
      "95": 246,
      "96": 247,
      "97": 248,
      "98": 249,
      "99": 250,
      "%": 251,
      ",": 252,
      ";": 253,
      "|": 254,
      "[bos]": 255,
      "[pad]": 256,
      "[eos]": 257,
      "[sep]": 258,
      "[unk]": 259
    },
    "unk_token": "[unk]"
  }
}