<start_of_turn>user
Only reply like a pirate.
What is the answer to life the universe and everything?<end_of_turn>
<start_of_turn>model
Arrr, 'tis 42,<end_of_turn>
[[["わかりやすい","easyToUnderstand","thumb-up"],["問題の解決に役立った","solvedMyProblem","thumb-up"],["その他","otherUp","thumb-up"]],[["必要な情報がない","missingTheInformationINeed","thumb-down"],["複雑すぎる / 手順が多すぎる","tooComplicatedTooManySteps","thumb-down"],["最新ではない","outOfDate","thumb-down"],["翻訳に関する問題","translationIssue","thumb-down"],["サンプル / コードに問題がある","samplesCodeIssue","thumb-down"],["その他","otherDown","thumb-down"]],["最終更新日 2025-03-21 UTC。"],[],[],null,["# Gemma formatting and system instructions\n\nGemma instruction-tuned (IT) models are trained with a specific *formatter* that\nannotates all instruction tuning examples with extra information, both at\ntraining and inference time. The formatter has two purposes:\n\n1. Indicating roles in a conversation, such as the *system* , *user* , or *assistant* roles.\n2. Delineating turns in a conversation, especially in a multi-turn conversation.\n\nBelow, we specify the control tokens used by Gemma and their use cases. Note\nthat the control tokens are reserved in and specific to our tokenizer.\n\n- Token to indicate a user turn: `user`\n- Token to indicate a model turn: `model`\n- Token to indicate the beginning of dialogue turn: `\u003cstart_of_turn\u003e`\n- Token to indicate the end of dialogue turn: `\u003cend_of_turn\u003e`\n\nHere's an example dialogue: \n\n \u003cstart_of_turn\u003euser\n knock knock\u003cend_of_turn\u003e\n \u003cstart_of_turn\u003emodel\n who is there\u003cend_of_turn\u003e\n \u003cstart_of_turn\u003euser\n Gemma\u003cend_of_turn\u003e\n \u003cstart_of_turn\u003emodel\n Gemma who?\u003cend_of_turn\u003e\n\nThe token `\"\u003cend_of_turn\u003e\\n\"` is the turn separator, and the prompt prefix is\n`\"\u003cstart_of_turn\u003emodel\\n\"`. This means that if you'd like to prompt the model\nwith a question like, \"What is Cramer's Rule?\", you should instead feed the\nmodel as follows: \n\n \"\u003cstart_of_turn\u003euser\n What is Cramer's Rule?\u003cend_of_turn\u003e\n \u003cstart_of_turn\u003emodel\"\n\nNote that if you want to finetune the pretrained Gemma models with your own\ndata, you can use any such schema for control tokens, as long as it's consistent\nbetween your training and inference use cases.\n\nSystem instructions\n-------------------\n\nGemma's instruction-tuned models are designed to work with only two roles:\n`user` and `model`. Therefore, the `system` role or a system turn is not\nsupported.\n\nInstead of using a separate system role, provide system-level instructions\ndirectly within the initial user prompt. The model instruction following\ncapabilities allow Gemma to interpret the instructions effectively. For example: \n\n \u003cstart_of_turn\u003euser\n Only reply like a pirate.\n\n What is the answer to life the universe and everything?\u003cend_of_turn\u003e\n \u003cstart_of_turn\u003emodel\n Arrr, 'tis 42,\u003cend_of_turn\u003e"]]
