tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "(?<=.)"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "</s>": 1,
      "<unk>": 2,
      "A": 3,
      "L": 4,
      "G": 5,
      "V": 6,
      "S": 7,
      "R": 8,
      "E": 9,
      "D": 10,
      "T": 11,
      "I": 12,
      "P": 13,
      "K": 14,
      "F": 15,
      "Q": 16,
      "N": 17,
      "Y": 18,
      "M": 19,
      "H": 20,
      "W": 21,
      "C": 22,
      "X": 23,
      "B": 24,
      "O": 25,
      "U": 26,
      "Z": 27,
      "[MASK]": 28
    },
    "unk_token": "<unk>"
  }
}