tokenizer_config.json

{
  "tokenizer_class": "PreTrainedTokenizerFast",
  "model_type": "gpt2",
  "unk_token": {
    "content": "<unk>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "pad_token": {
    "content": "<pad>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "bos_token": {
    "content": "<s>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "</s>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "max_len": 512,
  "clean_up_tokenization_spaces": false
}