tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "<sep>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": "<|startoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13224": {
      "content": "<unused1>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13225": {
      "content": "<unused2>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13226": {
      "content": "<unused3>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13227": {
      "content": "<unused4>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13228": {
      "content": "<unused5>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13229": {
      "content": "<unused6>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13230": {
      "content": "<unused7>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13231": {
      "content": "<unused8>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13232": {
      "content": "<unused9>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13233": {
      "content": "<unused10>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13310": {
      "content": "<cls>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "13311": {
      "content": "<mask>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<unused1>",
    "<unused2>",
    "<unused3>",
    "<unused4>",
    "<unused5>",
    "<unused6>",
    "<unused7>",
    "<unused8>",
    "<unused9>",
    "<unused10>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      null,
      "tokenization_linglong_fast.LingLongTokenizerFast"
    ]
  },
  "bos_token": "<|startoftext|>",
  "chat_template": "{{ bos_token }}{{ \"问题：\" }}{{ messages[-1][\"content\"] }}{{ \"<unused1>答案：\" }}",
  "clean_up_tokenization_spaces": true,
  "cls_token": "<cls>",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "eos_token": "<|endoftext|>",
  "mask_token": "<mask>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "sep_token": "<sep>",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "LingLongTokenizer",
  "unk_token": "<unk>"
}