tokenizer_config.json

{
  "auto_map": {
    "AutoTokenizer": ["tokenization_helmbert.HELMBertTokenizer", null]
  },
  "added_tokens_decoder": {
    "0": {
      "content": " ",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "@",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "\n",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "§",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "¶",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "@",
  "clean_up_tokenization_spaces": false,
  "cls_token": "@",
  "eos_token": "\n",
  "extra_special_tokens": {},
  "mask_token": "¶",
  "model_max_length": 512,
  "pad_token": " ",
  "sep_token": "\n",
  "tokenizer_class": "HELMBertTokenizer",
  "unk_token": "§"
}