[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["缺少我需要的資訊","missingTheInformationINeed","thumb-down"],["過於複雜/步驟過多","tooComplicatedTooManySteps","thumb-down"],["過時","outOfDate","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["示例/程式碼問題","samplesCodeIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2024-08-05 (世界標準時間)。"],[],[],null,["Gemma is a family of lightweight, state-of-the-art open models built from the\nsame research and technology used to create the\n[Gemini](https://deepmind.google/technologies/gemini/#introduction) models.\nDeveloped by Google DeepMind and other teams across Google, Gemma is named after\nthe Latin *gemma*, meaning precious stone. The Gemma model weights are\nsupported by developer tools that promote innovation, collaboration, and the\nresponsible use of artificial intelligence (AI). You can get multiple variations\nof Gemma for general and specific use cases:\n\n- [**Gemma 3**](/gemma/docs/core): Solve a wide variety of generative AI tasks with text and image input, support for over 140 languages, and long 128K context window.\n- [**CodeGemma**](/gemma/docs/codegemma): Complete programming tasks with this lightweight, coding-focused generative model.\n- [**PaliGemma 2**](/gemma/docs/paligemma): Build visual data processing AI solutions with a model that's built to be fine-tuned for your image data processing applications and available in multiple resolutions.\n- [**ShieldGemma 2**](/gemma/docs/core): Evaluate the safety of generative AI models' input and output against defined policies.\n\nMany more Gemma variants are available from Google and our AI developer\ncommunity. Check them out on\n[Kaggle Models](https://www.kaggle.com/models?query=gemma) and\n[Hugging Face](https://huggingface.co/models?search=google/gemma).\nGet inspired by what our community members have built with Gemma in the\n[Gemmaverse](/gemma/gemmaverse).\n\nThe Gemma models are available to run in\nyour applications and on your hardware, mobile devices, or hosted services. You\ncan also customize these models using tuning techniques so that they excel at\nperforming specific tasks that matter to you and your users. Gemma models draw\ninspiration and technological lineage from the Gemini family of models, and are\nmade for the AI development community to extend and take further.\n\nReady to begin? **[Get started](/gemma/docs/get_started)** with Gemma models!"]]