tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32000": {
      "content": "#Address#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "#CarNumber#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "#CardNumber#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "#DateOfBirth#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32004": {
      "content": "#Email#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32005": {
      "content": "#PassportNumber#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32006": {
      "content": "#Person#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32007": {
      "content": "#Person1#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32008": {
      "content": "#Person2#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32009": {
      "content": "#Person3#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32010": {
      "content": "#Person4#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32011": {
      "content": "#Person5#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32012": {
      "content": "#Person6#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32013": {
      "content": "#Person7#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32014": {
      "content": "#PhoneNumber#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32015": {
      "content": "#SSN#",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32016": {
      "content": "<dialogue>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32017": {
      "content": "</dialogue>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32018": {
      "content": "<summary>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32019": {
      "content": "</summary>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "#Address#",
    "#CarNumber#",
    "#CardNumber#",
    "#DateOfBirth#",
    "#Email#",
    "#PassportNumber#",
    "#Person#",
    "#Person1#",
    "#Person2#",
    "#Person3#",
    "#Person4#",
    "#Person5#",
    "#Person6#",
    "#Person7#",
    "#PhoneNumber#",
    "#SSN#",
    "<dialogue>",
    "</dialogue>",
    "<summary>",
    "</summary>"
  ],
  "bos_token": "<s>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = \"당신은 고려대학교 NLP&AI 연구실에서 만든 AI 챗봇입니다. 당신의 이름은 'KULLM'으로, 한국어로는 '구름'을 뜻합니다. 당신은 비도덕적이거나, 성적이거나, 불법적이거나 또는 사회 통념적으로 허용되지 않는 발언은 하지 않습니다. 사용자와 즐겁게 대화하며, 사용자의 응답에 가능한 정확하고 친절하게 응답함으로써 최대한 도와주려고 노력합니다. 질문이 이상하다면, 어떤 부분이 이상한지 설명합니다. 거짓 정보를 발언하지 않도록 주의합니다.\" %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]'}}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "max_length": 4096,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "</s>",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "stride": 0,
  "tokenizer_class": "LlamaTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>",
  "use_default_system_prompt": true
}