tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|begin_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|end_of_text|>",
      "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
    },
    "65520": {
      "content": "<|text_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65521": {
      "content": "<|text_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65522": {
      "content": "<|ocr_correction_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65523": {
      "content": "<|ocr_correction_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65524": {
      "content": "<|translation_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65525": {
      "content": "<|translation_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65526": {
      "content": "<|pii_preview_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65527": {
      "content": "<|pii_preview_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65528": {
      "content": "<|pii_analysis_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65529": {
      "content": "<|pii_analysis_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65530": {
      "content": "<|pii_result_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65531": {
      "content": "<|pii_result_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|text_start|>",
    "<|text_end|>",
    "<|ocr_correction_start|>",
    "<|ocr_correction_end|>",
    "<|translation_start|>",
    "<|translation_end|>",
    "<|pii_preview_start|>",
    "<|pii_preview_end|>",
    "<|pii_analysis_start|>",
    "<|pii_analysis_end|>",
    "<|pii_result_start|>",
    "<|pii_result_end|>"
  ],
  "clean_up_tokenization_spaces": true,
  "model_max_length": 1000000000000000019884624838656,
  "tokenizer_class": "PreTrainedTokenizerFast"
}