tokenizer_config.json

{
  "add_prefix_space": false,
  "added_token_decoder": {
    "0": {
      "content": "<|paddingtoken|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "1": {
      "content": "<|startoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "2": {
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "3": {
      "content": "<|masktoken|>",
      "single_word": false,
      "lstrip": true,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    "4": {
      "content": "<|unknowntoken|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": false,
  "extra_special_tokens": {},
  "model_max_length": 16384,
  "use_fast": true,
  "tokenizer_class": "GPT2TokenizerFast",
  "bos_token": "<|startoftext|>",
  "eos_token": "<|endoftext|>",
  "unk_token": "<|unknowntoken|>",
  "sep_token": "<|endoftext|>",
  "pad_token": "<|paddingtoken|>",
  "cls_token": "<|startoftext|>",
  "mask_token": "<|masktoken|>"
}