{"id":5440,"date":"2024-09-16T06:17:00","date_gmt":"2024-09-15T21:17:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5440"},"modified":"2024-09-16T06:17:00","modified_gmt":"2024-09-15T21:17:00","slug":"data-gemma","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5440","title":{"rendered":"Data Gemma"},"content":{"rendered":"\n<p>Google\u304b\u3089\u767a\u8868\u3055\u308c\u305fDataGemma\u3082\u8208\u5473\u6df1\u3044\u53d6\u308a\u7d44\u307f\uff08<a href=\"https:\/\/blog.google\/technology\/ai\/google-datagemma-ai-llm\/\">DataGemma: AI open models connecting LLMs to Google\u2019s Data Commons (blog.google)<\/a>\u3001<a href=\"https:\/\/research.google\/blog\/grounding-ai-in-reality-with-a-little-help-from-data-commons\/\">Grounding AI in reality with a little help from Data Commons (research.google)<\/a>\uff09\u3067\u3042\u308b\u3002<\/p>\n\n\n\n<p><a href=\"https:\/\/datacommons.org\/\">Home &#8211; Data Commons<\/a>\u3092\u5229\u7528\u3057\u3066\u30cf\u30eb\u30b7\u30cd\u30fc\u30b7\u30e7\u30f3\u3092\u6291\u3048\u3088\u3046\u3068\u3044\u3046\u3082\u306e\u3067RIG (Retrieval-Interleaved Generation) \u3068RAG (Retrieval-Augmented Generation) \u306e\u30e6\u30fc\u30b9\u30b1\u30fc\u30b9\u3092\u60f3\u5b9a\u3002\u30e2\u30c7\u30eb\u306f<a href=\"https:\/\/huggingface.co\/google\/datagemma-rig-27b-it\">google\/datagemma-rig-27b-it \u00b7 Hugging Face<\/a>\u3001<a href=\"https:\/\/huggingface.co\/google\/datagemma-rag-27b-it\">google\/datagemma-rag-27b-it \u00b7 Hugging Face<\/a>\u306b\u516c\u958b\u308c\u3066\u3044\u308b\u3002<\/p>\n\n\n\n<p>\u4e0a\u8a18\u30e2\u30c7\u30eb\u306fRIG\u3067\u3042\u308c\u3070\u300cThe DataGemma model (based on the 27 billion parameter Gemma 2 model and fully fine-tuned for this RIG task) generates a response, which includes a natural language query for Data Commons&#8217; existing natural language interface, specifically designed to retrieve relevant data. For example, instead of stating &#8220;The population of California is 39 million&#8221;, the model would produce &#8220;The population of California is [DC(What is the population of California?) \u2192 &#8220;39 million&#8221;]&#8221;, allowing for external verification and increased accuracy.\u300d\u3001RAG\u3067\u3042\u308c\u3070\u300cThe DataGemma model (based on the Gemma 2 (27B) model and fully fine-tuned for this RAG task) analyzes the user&#8217;s query and generates a corresponding query (or queries) in natural language that can be understood by Data Commons&#8217; existing natural language interface.\u300d\u3068\u306e\u3053\u3068\u3067Data Commons\u306e\u65e2\u5b58\u30a4\u30f3\u30bf\u30d5\u30a7\u30fc\u30b9\u3092\u3046\u307e\u304f\u6d3b\u7528\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u3063\u3066\u3044\u308b\u3002<\/p>\n\n\n\n<p>\u3053\u306e\u624b\u306efine tuning\u306f\u91cd\u8981\u306b\u306a\u308a\u3064\u3064\u3042\u308b\u3088\u3046\u306b\u601d\u3046\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google\u304b\u3089\u767a\u8868\u3055\u308c\u305fDataGemma\u3082\u8208\u5473\u6df1\u3044\u53d6\u308a\u7d44\u307f\uff08DataGemma: AI open models connecting LLMs to Google\u2019s Data Commons (blog.googl &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=5440\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;Data Gemma&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[138,324],"class_list":["post-5440","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-fact-checking","tag-rag"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5440","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5440"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5440\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5440"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5440"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5440"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}