tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100000": {
      "content": "<|startofpiece|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100001": {
      "content": "<|endofpiece|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100002": {
      "content": "<|LDWANG|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100003": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100004": {
      "content": "[gMASK]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100005": {
      "content": "[sMASK]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "100006": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100007": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "[CLS]",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "legacy": false,
  "model_max_length": 2048,
  "pad_token": "<|endoftext|>",
  "padding_side": "right",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}