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
    }
  },
  "additional_special_tokens": [],
  "bos_token": "<s>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}\n{% set loop_messages = messages[1:] %}\n{% set system_message = messages[0]['content'] %}\n{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}\n{% set loop_messages = messages %}\n{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}\n{% else %}\n{% set loop_messages = messages %}\n{% set system_message = false %}\n{% endif %}\n{% if not (messages[0]['role'] == 'assistant' and loop_messages|length > 0) %}\n{{ bos_token }}\n{% endif %}\n{% for message in loop_messages %}\n{% if (message['role'] == 'user') != ((loop.index0 + (1 if messages[0]['role'] == 'assistant' else 0)) % 2 == 0) %}\n{{ raise_exception('Conversation roles must alternate starting from the first role.') }}\n{% endif %}\n{% if loop.index0 == 0 and system_message != false %}\n{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}\n{% else %}\n{% set content = message['content'] %}\n{% endif %}\n{% if message['role'] == 'user' %}\n{{ '[INST] ' + content.strip() + ' [/INST] ' }}\n{% elif message['role'] == 'system' %}\n{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}\n{% elif message['role'] == 'assistant' %}\n{{ ''  + content.strip() + '' + eos_token }}\n{% endif %}\n{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "legacy": true,
  "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": "left",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}