tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "[S1]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "2": {
      "content": "[S2]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "clean_up_tokenization_spaces": false,
  "extra_special_tokens": {},
  "max_length": 1024,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "processor_class": "DiaProcessor",
  "tokenizer_class": "DiaTokenizer",
  "unk_token": "<pad>"
}