tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50000": {
      "content": "<EOL>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50001": {
      "content": "<|UNKNOWN|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "errors": "replace",
  "full_tokenizer_file": null,
  "model_max_length": 1024,
  "pad_token": "<pad>",
  "sep_token": "<EOL>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|UNKNOWN|>"
}