tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "54354": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "54355": {
      "content": "<|bos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "54356": {
      "content": "<|eos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "54357": {
      "content": "<|sep|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|bos|>",
    "<|eos|>",
    "<|sep|>"
  ],
  "bos_token": "<|bos|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|eos|>",
  "errors": "replace",
  "model_max_length": 1024,
  "pad_token": null,
  "sep_token": "<|sep|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}