tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "max_length": 1024,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": {
    "strategy": {
      "Fixed": 1024
    },
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 0,
    "pad_type_id": 0,
    "pad_token": "<|pad|>"
  },
  "added_tokens": [
    {
      "id": 0,
      "special": true,
      "content": "<|pad|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 1,
      "special": true,
      "content": "<|bos|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 2,
      "special": true,
      "content": "<|eos|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 30,
      "special": false,
      "content": "<|pf00002|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true
    },
    {
      "id": 31,
      "special": false,
      "content": "<|pf00042|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true
    },
    {
      "id": 32,
      "special": false,
      "content": "<|pf00125|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true
    },
    {
      "id": 33,
      "special": false,
      "content": "<|pf00127|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true
    },
    {
      "id": 34,
      "special": false,
      "content": "<|pf00257|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true
    },
    {
      "id": 35,
      "special": false,
      "content": "<|pf00262|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true
    },
    {
      "id": 36,
      "special": false,
      "content": "<|pf03668|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true
  },
  "post_processor": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "vocab": {
      "<|pad|>": 0,
      "<|bos|>": 1,
      "<|eos|>": 2,
      "1": 3,
      "2": 4,
      "A": 5,
      "B": 6,
      "C": 7,
      "D": 8,
      "E": 9,
      "F": 10,
      "G": 11,
      "H": 12,
      "I": 13,
      "K": 14,
      "L": 15,
      "M": 16,
      "N": 17,
      "O": 18,
      "P": 19,
      "Q": 20,
      "R": 21,
      "S": 22,
      "T": 23,
      "U": 24,
      "V": 25,
      "W": 26,
      "X": 27,
      "Y": 28,
      "Z": 29
    },
    "merges": []
  }
}