tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 512,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<UNK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<SEP>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<MASK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<CLS>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<PAD>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": {
    "type": "RobertaProcessing",
    "sep": [
      "<SEP>",
      1
    ],
    "cls": [
      "<CLS>",
      3
    ],
    "trim_offsets": true,
    "add_prefix_space": true
  },
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<UNK>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "<UNK>": 0,
      "<SEP>": 1,
      "<MASK>": 2,
      "<CLS>": 3,
      "<PAD>": 4,
      "A": 5,
      "B": 6,
      "C": 7,
      "D": 8,
      "G": 9,
      "H": 10,
      "K": 11,
      "M": 12,
      "N": 13,
      "R": 14,
      "S": 15,
      "T": 16,
      "V": 17,
      "W": 18,
      "Y": 19
    },
    "merges": []
  }
}