tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<|mask|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|bos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|eos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|bos|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|eos|>",
  "mask_token": "<|mask|>",
  "model_max_length": 256,
  "pad_token": "<|pad|>",
  "return_tensors": "pt",
  "tokenizer_class": "PreTrainedTokenizerFast"
}