tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": true,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12560": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12561": {
      "content": "<|bos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12562": {
      "content": "<|eos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12563": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|bos|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|eos|>",
  "extra_special_tokens": {},
  "model_max_length": 1024,
  "pad_token": "<|pad|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}