tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<|padding|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "[MASK]",
      "lstrip": true,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<|UNUSED_0|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<|UNUSED_1|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "<|UNUSED_2|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": "<|UNUSED_3|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "11": {
      "content": "<|UNUSED_4|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12": {
      "content": "<|UNUSED_5|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13": {
      "content": "<|UNUSED_6|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "14": {
      "content": "<|UNUSED_7|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "15": {
      "content": "<|UNUSED_8|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "16": {
      "content": "<|UNUSED_9|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "17": {
      "content": "<|UNUSED_10|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "18": {
      "content": "<|UNUSED_11|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "19": {
      "content": "<|UNUSED_12|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "20": {
      "content": "<|UNUSED_13|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "21": {
      "content": "<|UNUSED_14|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "22": {
      "content": "<|UNUSED_15|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "23": {
      "content": "<|HISTORY|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "24": {
      "content": "<|PHONE_NUMBER|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "25": {
      "content": "<|EMAIL|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "26": {
      "content": "<|IP_ADDRESS|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "27": {
      "content": "<|URL|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "28": {
      "content": "<|DATE|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "29": {
      "content": "<|TIME|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|UNUSED_0|>",
    "<|UNUSED_1|>",
    "<|UNUSED_2|>",
    "<|UNUSED_3|>",
    "<|UNUSED_4|>",
    "<|UNUSED_5|>",
    "<|UNUSED_6|>",
    "<|UNUSED_7|>",
    "<|UNUSED_8|>",
    "<|UNUSED_9|>",
    "<|UNUSED_10|>",
    "<|UNUSED_11|>",
    "<|UNUSED_12|>",
    "<|UNUSED_13|>",
    "<|UNUSED_14|>",
    "<|UNUSED_15|>",
    "<|HISTORY|>",
    "<|PHONE_NUMBER|>",
    "<|EMAIL|>",
    "<|IP_ADDRESS|>",
    "<|URL|>",
    "<|DATE|>",
    "<|TIME|>"
  ],
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "extra_special_tokens": {},
  "mask_token": "[MASK]",
  "max_len": 512,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 8192,
  "pad_token": "[PAD]",
  "padding_side": "right",
  "return_tensors": "pt",
  "sep_token": "[SEP]",
  "tokenizer_class": "PreTrainedTokenizer",
  "truncation": true,
  "unk_token": "[UNK]"
}