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
    },
    "3": {
      "content": "<MASK|LLM-jp>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<PAD|LLM-jp>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<CLS|LLM-jp>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<SEP|LLM-jp>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<EOD|LLM-jp>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "chat_template": "{{ bos_token }}\n{%- for message in messages %}\n    {%- if message['role'] == 'user' %}\n        {{- '\nユーザー:\n' + message['content'] }}\n    {%- elif message['role'] == 'system' %}\n        {%- if 'content' in message %}\n            {{- message['content'] }}\n        {%- else %}\n            {{- 'アシスタント:\n私はアシスタントチャットボットとしてユーザーの命令に従います。\n<think>ここで慎重に考える</think><answer>答え</answer> のように、<think></think><answer></answer> の形式で思考過程とファイナルアンサーを回答します。' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- '\nアシスタント:\n' + message['content'] + eos_token }}\n    {%- endif %}\n\n    {{- '\n' }}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- '\nアシスタント:\n' }}\n{%- endif %}",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<CLS|LLM-jp>",
  "eod_token": "</s>",
  "eos_token": "</s>",
  "extra_ids": 0,
  "extra_special_tokens": {},
  "mask_token": "<MASK|LLM-jp>",
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<PAD|LLM-jp>",
  "sep_token": "<SEP|LLM-jp>",
  "sp_model_kwargs": {},
  "tokenizer_class": "PreTrainedTokenizerFast",
  "unk_token": "<unk>"
}