tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "250100": {
      "content": "\n",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "250101": {
      "content": "\t",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "250102": {
      "content": "<|space|><|space|><|space|><|space|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "250103": {
      "content": "<|space|><|space|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "250104": {
      "content": "<|space|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "\n",
    "\t",
    "<|space|><|space|><|space|><|space|>",
    "<|space|><|space|>",
    "<|space|>"
  ],
  "bos_token": "▁start",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "extra_ids": 0,
  "max_length": 1024,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "sp_model_kwargs": {},
  "stride": 0,
  "tokenizer_class": "T5Tokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>"
}