tokenizer_config.json

{
  "added_tokens_decoder": {
    "5157": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6246": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7105": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "model_max_length": 512,
  "pad_token": "<pad>",
  "separate_vocabs": false,
  "source_lang": null,
  "sp_model_kwargs": {},
  "target_lang": null,
  "tokenizer_class": "MarianTokenizer",
  "unk_token": "<unk>"
}