ProtGPT3-1.3B/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<|pad|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<|bos|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<|eos|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 31,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 32,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 33,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<|pad|>": 0,
      "<|bos|>": 1,
      "<|eos|>": 2,
      "[UNK]": 3,
      "1": 4,
      "2": 5,
      "A": 6,
      "B": 7,
      "C": 8,
      "D": 9,
      "E": 10,
      "F": 11,
      "G": 12,
      "H": 13,
      "I": 14,
      "K": 15,
      "L": 16,
      "M": 17,
      "N": 18,
      "O": 19,
      "P": 20,
      "Q": 21,
      "R": 22,
      "S": 23,
      "T": 24,
      "U": 25,
      "V": 26,
      "W": 27,
      "X": 28,
      "Y": 29,
      "Z": 30
    },
    "unk_token": "[UNK]"
  }
}