tokenizer_config.json

{
  "added_tokens_decoder": {
    "59": {
      "content": "<s>",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "60": {
      "content": "</s>",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "61": {
      "content": "<unk>",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "62": {
      "content": "<pad>",
      "lstrip": true,
      "normalized": true,
      "rstrip": true,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "extra_ids": 0,
  "max_len": 128,
  "model_max_length": 128,
  "pad_token": "<pad>",
  "tokenizer_class": "CustomTokenizer",
  "unk_token": "<unk>"
}