tokenizer_config.json

{
  "add_prefix_space": true,
  "added_tokens_decoder": {
    "3": {
      "content": "<BOS>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<EOS>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<PAD>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<CLS>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<SEP>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<EOD>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "<MASK>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2000": {
      "content": "<UNK>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<EOD>"
  ],
  "bos_token": "<BOS>",
  "clean_up_tokenization_spaces": true,
  "cls_token": "<CLS>",
  "eos_token": "<EOS>",
  "extra_ids": 0,
  "legacy": true,
  "mask_token": "<MASK>",
  "model_max_length": 2048,
  "pad_token": "<PAD>",
  "sep_token": "<SEP>",
  "sp_model_kwargs": {},
  "split_special_tokens": true,
  "tokenizer_class": "T5Tokenizer",
  "unk_token": "<UNK>"
}