{"id":5620,"date":"2024-10-17T06:00:00","date_gmt":"2024-10-16T21:00:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5620"},"modified":"2024-10-17T06:00:00","modified_gmt":"2024-10-16T21:00:00","slug":"matmamba-a-matryoshka-state-space-model","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5620","title":{"rendered":"MatMamba: A Matryoshka State Space Model"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>MatMamba: A Matryoshka State Space Model\u00a0<\/strong>[24.9]<br>MatMamba\u306fMatryoshka\u30b9\u30bf\u30a4\u30eb\u306e\u5b66\u7fd2\u3068Mamba2\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u72b6\u614b\u7a7a\u9593\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002 MatMamba\u306f\u3001\u69d8\u3005\u306a\u30e2\u30c7\u30eb\u30b5\u30a4\u30ba\u306b\u307e\u305f\u304c\u308b\u52b9\u7387\u7684\u3067\u9069\u5fdc\u7684\u306a\u30c7\u30d7\u30ed\u30a4\u30e1\u30f3\u30c8\u3092\u53ef\u80fd\u306b\u3059\u308b\u3002 \u8a00\u8a9e\u30e2\u30c7\u30eb\u3068\u753b\u50cf\u30e2\u30c7\u30eb\u306f,35M\u304b\u30891.4B\u307e\u3067\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u30b5\u30a4\u30ba\u3067\u8a13\u7df4\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.06718v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.06718v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 09 Oct 2024 09:41:34 GMT)<\/li>\n\n\n\n<li>\u30de\u30c8\u30ea\u30e7\u30fc\u30b7\u30ab\u69cb\u9020\u306eMamba\u3001\u300cWe train a single large MatMamba model and are able to get a number of smaller nested models for free \u2013 while maintaining or improving upon the performance of a baseline smaller model trained from scratch.\u300d\u3068\u3044\u3046\u5229\u70b9\u304c\u3042\u308b\u3002\u52a0\u3048\u3066\uff08Mamba\u3060\u304b\u3089\uff09\u9ad8\u89e3\u50cf\u5ea6\u3067\u306fViT\u3088\u308a\u512a\u308c\u3066\u3044\u308b\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/ScaledFoundations\/MatMamba\">GitHub &#8211; ScaledFoundations\/MatMamba: Code and pretrained models for the paper: &#8220;MatMamba: A Matryoshka State Space Model&#8221;<\/a><\/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":[235,376],"class_list":["post-5620","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mamba","tag-ssm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5620","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=5620"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5620\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5620"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5620"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5620"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}