tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "\u0000",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57344": {
      "content": "",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57345": {
      "content": "",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57347": {
      "content": "",
      "lstrip": true,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "",
  "clean_up_tokenization_spaces": true,
  "cls_token": "",
  "eos_token": "",
  "mask_token": "",
  "model_max_length": 2048,
  "pad_token": "\u0000",
  "sep_token": "",
  "tokenizer_class": "CanineTokenizer"
}