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
    },
    "65514": {
      "content": "<|language|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65515": {
      "content": "<|synopsis|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65516": {
      "content": "<|keywords|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65517": {
      "content": "<|title_english|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65518": {
      "content": "<|title_original|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65519": {
      "content": "<|format|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65520": {
      "content": "<|audience|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65521": {
      "content": "<|discipline|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65522": {
      "content": "<|sentiment|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65523": {
      "content": "<|brand|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65524": {
      "content": "<|time|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65525": {
      "content": "<|location|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65526": {
      "content": "<|country|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65527": {
      "content": "<|protagonist|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65528": {
      "content": "<|other_character|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65529": {
      "content": "<|bibliography|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65530": {
      "content": "<|quote|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65531": {
      "content": "<|link|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65532": {
      "content": "<|text_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65533": {
      "content": "<|text_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65534": {
      "content": "<|annotation_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65535": {
      "content": "<|annotation_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|language|>",
    "<|synopsis|>",
    "<|keywords|>",
    "<|title_english|>",
    "<|title_original|>",
    "<|format|>",
    "<|audience|>",
    "<|discipline|>",
    "<|sentiment|>",
    "<|brand|>",
    "<|time|>",
    "<|location|>",
    "<|country|>",
    "<|protagonist|>",
    "<|other_character|>",
    "<|bibliography|>",
    "<|quote|>",
    "<|link|>",
    "<|text_start|>",
    "<|text_end|>",
    "<|annotation_start|>",
    "<|annotation_end|>"
  ],
  "clean_up_tokenization_spaces": true,
  "model_max_length": 1000000000000000019884624838656,
  "tokenizer_class": "PreTrainedTokenizerFast"
}