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": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "auto_map": {
    "AutoTokenizer": [
      "tokenizer.LCATokenizer",
      null
    ]
  },
  "clean_up_tokenization_spaces": false,
  "cls_token": "[CLS]",
  "extra_special_tokens": {},
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "tokenizer_class": "LCATokenizer",
  "unk_token": "[UNK]",
  "kmer": 6,
  "shift": 1,
  "operation_space": "kmer"
}