tokenizer_config.json

{
  "added_tokens_decoder": {
    "1": {
      "content": "[pad]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "[unk]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[cls]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "[mask]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "[bos]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "[eos]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "[bos]",
  "clean_up_tokenization_spaces": true,
  "cls_token": "[cls]",
  "do_lower_case": false,
  "eos_token": "[eos]",
  "mask_token": "[mask]",
  "model_max_length": 1024,
  "pad_token": "[pad]",
  "tokenizer_class": "CharTokenizer",
  "unk_token": "[unk]",
  "auto_map": {
    "AutoTokenizer": ["char_tokenizer.CharTokenizer", null]
  }
}