{"id":5820,"date":"2024-12-06T05:10:00","date_gmt":"2024-12-05T20:10:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5820"},"modified":"2024-12-06T05:10:00","modified_gmt":"2024-12-05T20:10:00","slug":"mh-moemulti-head-mixture-of-experts","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5820","title":{"rendered":"MH-MoE:Multi-Head Mixture-of-Experts\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>MH-MoE:Multi-Head Mixture-of-Experts\u00a0<\/strong>[119.5]<br>MH-MoE(Multi-Head Mixture-of-Experts)\u306f,\u30de\u30eb\u30c1\u30d8\u30c3\u30c9\u6a5f\u69cb\u3092\u7528\u3044\u3066, \u7570\u306a\u308b\u5c02\u9580\u5bb6\u5185\u306e\u69d8\u3005\u306a\u8868\u73fe\u7a7a\u9593\u304b\u3089\u306e\u60c5\u5831\u3092\u96c6\u7d04\u3057, \u512a\u308c\u305f\u6027\u80fd\u3092\u793a\u3059\u3002 FLOP\u3068\u30d1\u30e9\u30e1\u30fc\u30bf\u30d1\u30ea\u30c6\u30a3\u306e\u4e21\u65b9\u3092\u30b9\u30d1\u30fc\u30b9\u30df\u30ad\u30b5\u30fc\u30e2\u30c7\u30eb\u3067\u7dad\u6301\u3059\u308bMH-MoE\u306e\u65b0\u305f\u306a\u5b9f\u88c5\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2411.16205v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2411.16205v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 25 Nov 2024 09:05:36 GMT)<\/li>\n\n\n\n<li><a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2404.15045v1\">Fugu-MT \u8ad6\u6587\u7ffb\u8a33(\u6982\u8981): Multi-Head Mixture-of-Experts<\/a> \u306e\u5b9f\u88c5\u306e\u6539\u5584<\/li>\n\n\n\n<li>\u300cIn this paper, we present a novel implementation of MH-MoE that maintains both FLOPs and parameter parity with sparse Mixture of Experts models.\u300d<\/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":[250],"class_list":["post-5820","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mixture-of-experts"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5820","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=5820"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5820\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5820"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5820"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5820"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}