tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [],
  "auto_map": {
    "AutoTokenizer": [
      "midm_bitext_tokenization.Midm_bitext_Tokenizer",
      null
    ]
  },
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "extra_ids": 0,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "sp_model_kwargs": {},
  "tokenizer_class": "Midm_bitext_Tokenizer",
  "unk_token": "<unk>"
}