{"id":5791,"date":"2024-11-27T05:03:00","date_gmt":"2024-11-26T20:03:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5791"},"modified":"2024-11-27T05:03:00","modified_gmt":"2024-11-26T20:03:00","slug":"codexembed-a-generalist-embedding-model-family-for-multiligual-and-multi-task-code-retrieval","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5791","title":{"rendered":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval\u00a0<\/strong>[87.2]<br>CodeXEmbed\u306f400M\u304b\u30897B\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u5927\u898f\u6a21\u306a\u30b3\u30fc\u30c9\u57cb\u3081\u8fbc\u307f\u30e2\u30c7\u30eb\u306e\u30d5\u30a1\u30df\u30ea\u30fc\u3067\u3042\u308b\u3002 \u6211\u3005\u306e\u65b0\u3057\u3044\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u306f\u3001\u8907\u6570\u306e\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u8a00\u8a9e\u3092\u7d71\u5408\u3057\u3001\u69d8\u3005\u306a\u30b3\u30fc\u30c9\u95a2\u9023\u30bf\u30b9\u30af\u3092\u5171\u901a\u306e\u691c\u7d22\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306b\u5909\u63db\u3059\u308b\u3002 \u79c1\u305f\u3061\u306e7B\u30e2\u30c7\u30eb\u306f\u3001\u30b3\u30fc\u30c9\u691c\u7d22\u306b\u304a\u3044\u3066\u65b0\u3057\u3044\u6700\u5148\u7aef(SOTA)\u3092\u8a2d\u5b9a\u3057\u3001\u4ee5\u524d\u306e\u4e3b\u8981\u306a\u30e2\u30c7\u30eb\u3067\u3042\u308bVoyage-Code\u3092CoIR\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306720%\u4ee5\u4e0a\u4e0a\u56de\u3063\u3066\u3044\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2411.12644v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2411.12644v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 19 Nov 2024 16:54:45 GMT)<\/li>\n\n\n\n<li>Code RAG\u306a\u3069\u3067\u91cd\u8981\u306b\u306a\u308b\u304c\u96e3\u3057\u3044\u30bf\u30b9\u30af\u3067\u3042\u308bEmbedding\u30e2\u30c7\u30eb\u306e\u63d0\u6848\u3001\u300cOur 7B model sets a new state-ofthe-art (SOTA) in code retrieval, outperforming the previous leading model, Voyage-Code, by over 20% on CoIR benchmark.\u300d\u3068\u306e\u3053\u3068\u30022B\u306e\u30d9\u30fc\u30b9\u30e2\u30c7\u30eb\u306fgemma-2-2b-it\u30017B\u3060\u3068Mistral-7B-Instruct-v0.3\u306a\u3069\u30d9\u30fc\u30b9\u306f\u69d8\u3005\u3002<\/li>\n\n\n\n<li>\u73fe\u72b6\u30e2\u30c7\u30eb\u306f\u516c\u958b\u3055\u308c\u3066\u3044\u306a\u3044\u3063\u307d\u3044\u304c\u3001\u300cBy bridging the gap between text and code retrieval domains and releasing our models to the community, we aim to promote further research and innovation in developer tools and programming language understanding.\u300d\u306e\u3068\u8a18\u8f09\u304c\u3042\u308b\u3002<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[69,124],"class_list":["post-5791","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-code-generation","tag-embedding"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5791","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=5791"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5791\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5791"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5791"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5791"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}