tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_special_tokens": true,
  "additional_special_tokens": [
    "0",
    "1",
    "2",
    "3",
    "4",
    "5",
    "6",
    "7",
    "8",
    "9",
    "▁▁",
    "▁▁▁▁",
    "▁▁▁▁▁▁▁▁",
    "▁▁▁▁▁▁▁▁▁▁▁▁",
    "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
    " ",
    " ",
    "⁂",
    "─",
    "***",
    "----",
    "▁\"",
    "▁Author",
    "▁Title",
    "▁Tags",
    "▁Genre",
    "▁Style",
    "▁Knowledge",
    "▁Summary",
    "▁Rating",
    "Type",
    "Characters",
    "Glossary",
    "<|spmspace|>",
    "<|spmspace|><|spmspace|>",
    "<|spmspace|><|spmspace|><|spmspace|><|spmspace|>",
    "<|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|>",
    "<|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|>",
    "<|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|><|spmspace|>",
    "<|mtvocab|>",
    "<|mtvenglish|>",
    "<|mtvjapanese|>",
    "<|mtsentence|>",
    "<|mtsjapanese|>",
    "<|mtsenglish|>",
    "<|mtsentenceend|>",
    "<|mtvocabend|>",
    "<|mtend|>",
    "<|mask|>",
    "<|masksingle|>",
    "<|maskshort|>",
    "<|maskmedium|>",
    "<|masklong|>",
    "<|maskparagraph|>",
    "<|maskend|>",
    "<|fill|>",
    "<|fillend|>",
    "<|rubycover|>",
    "<|rubystart|>",
    "<|rubyend|>",
    "<|reserved0|>",
    "<|reserved1|>",
    "<|reserved2|>",
    "<|reserved3|>",
    "<|reserved4|>",
    "<|reserved5|>",
    "<|reserved6|>",
    "<|reserved7|>",
    "<|reserved8|>",
    "<|reserved9|>",
    "<|reserved10|>"
  ],
  "bos_token": {
    "__type": "AddedToken",
    "content": "<|startoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "legacy": true,
  "model_max_length": 8192,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<|pad|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "truncation": false,
  "unk_token": {
    "__type": "AddedToken",
    "content": "<|unknown|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}