tokenizer_config.json

{
  "added_tokens_decoder": {
    "1024": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1025": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1026": {
      "content": "<::::>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1027": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "sep_token": "<::::>",
  "sp_model_kwargs": {},
  "tokenizer_class": "BertGenerationTokenizer",
  "unk_token": "<unk>"
}