tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<mask>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<bos>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<eos>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "auto_map": {
    "AutoTokenizer": [
      "tokenizer.ProteinTokenizer",
      null
    ]
  },
  "bos_token": "<bos>",
  "bos_token_id": 3,
  "clean_up_tokenization_spaces": false,
  "eos_token": "<eos>",
  "eos_token_id": 4,
  "mask_token": "<mask>",
  "mask_token_id": 2,
  "model_input_names": [
    "input_ids",
    "attention_mask",
    "special_tokens_mask"
  ],
  "model_max_length": 2048,
  "other_special_token_ids": null,
  "pad_token": "<pad>",
  "pad_token_id": 0,
  "padding_side": "right",
  "tokenizer_class": "ProteinTokenizer",
  "truncation_side": "right",
  "unk_token": "<unk>",
  "unk_token_id": 1,
  "vocab": {
    "<bos>": 3,
    "<eos>": 4,
    "<mask>": 2,
    "<pad>": 0,
    "<unk>": 1,
    "A": 7,
    "B": 26,
    "C": 25,
    "D": 15,
    "E": 11,
    "F": 20,
    "G": 8,
    "H": 23,
    "I": 14,
    "K": 17,
    "L": 6,
    "M": 22,
    "N": 19,
    "P": 16,
    "Q": 18,
    "R": 12,
    "S": 10,
    "T": 13,
    "V": 9,
    "W": 24,
    "Y": 21,
    "|": 5
  }
}