tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": true,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "5": {
      "content": "<|mask|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "7": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "8": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "9": {
      "content": "<|ipython|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "10": {
      "content": "<|endofmessage|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "11": {
      "content": "<|python_call|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "12": {
      "content": "<|reserved_6|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "13": {
      "content": "<|reserved_7|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "14": {
      "content": "<|reserved_8|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "15": {
      "content": "<|reserved_9|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<s>",
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if not date_string is defined %}{% if strftime_now is defined %}{% set date_string = strftime_now(\"%Y년 %m월 %d일, %H시 %M분\") %}{% else %}{% set date_string = \"2024년 10월 19일, 12시 49분\" %}{% endif %}{% endif %}{{ '<|system|>\n저는 ETRI 언어지능연구실에서 개발한 eGPT 언어모델입니다. eGPT 언어모델은 70억 미만의 모델에서 복잡한 일을 처리할 수 있도록 개발 중입니다.\n\n지식 중단 일자: 이 모델은 2022년 12월 이전의 지식으로만 학습되었습니다.\n현재 날짜 및 시간: ' + date_string + '<|endoftext|>' if messages and messages[0]['role'] != 'system' }}{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|endoftext|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|endoftext|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|endoftext|>\n'}}{% elif message['role'] == 'ipython' or message['role'] == 'tool' %}{{'<|ipython|>\n' + message['content'] + '<|endoftext|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "endoftext_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false,
    "special": true
  },
  "eos_token": "</s>",
  "legacy": false,
  "mask_token": "<|mask|>",
  "model_max_length": 16384,
  "pad_token": "<pad>",
  "padding_side": "left",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}