{"id":3589,"date":"2023-07-25T05:16:00","date_gmt":"2023-07-24T20:16:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3589"},"modified":"2023-07-25T05:16:00","modified_gmt":"2023-07-24T20:16:00","slug":"alpagasus-training-a-better-alpaca-with-fewer-data","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3589","title":{"rendered":"AlpaGasus: Training A Better Alpaca with Fewer Data"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>AlpaGasus: Training A Better Alpaca with Fewer Data\u00a0<\/strong>[106.9]<br>52k\u306eAlpaca\u30c7\u30fc\u30bf\u304b\u3089\u30d5\u30a3\u30eb\u30bf\u3057\u305f9k\u306e\u9ad8\u54c1\u8cea\u30c7\u30fc\u30bf\u306e\u307f\u3092\u5fae\u8abf\u6574\u3057\u305fAlpaGasus\u3092\u7d39\u4ecb\u3059\u308b\u3002 AlpaGasus \u306f\u3001\u8907\u6570\u306e\u30c6\u30b9\u30c8\u30bb\u30c3\u30c8\u3067 GPT-4 \u3067\u8a55\u4fa1\u3055\u308c\u305f\u30aa\u30ea\u30b8\u30ca\u30eb\u306e Alpaca \u3092\u8457\u3057\u304f\u4e0a\u56de\u3063\u3066\u3044\u308b\u3002 \u307e\u305f\u30015.7\u500d\u9ad8\u901f\u306a\u8a13\u7df4\u3082\u63d0\u4f9b\u3057\u30017B\u578b\u306e\u8a13\u7df4\u6642\u9593\u309280\u5206(\u30a2\u30eb\u30d1\u30ab\u7528)\u304b\u308914\u5206\u306b\u77ed\u7e2e\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2307.08701v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2307.08701v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 17 Jul 2023 17:59:40 GMT)<\/li>\n\n\n\n<li>LLM\u3092\u7528\u3044\u3066instruction-finetuning\u7528\u30c7\u30fc\u30bf\u3092\u9ad8\u54c1\u8cea\u5316\u3001\u54c1\u8cea\u306e\u9ad8\u3044\u5c11\u6570\u30c7\u30fc\u30bf\u306e\u5229\u7528\u304c\u6709\u52b9\u3060\u3063\u305f\u3068\u3044\u3046\u5831\u544a\u3002instruction-finetuning\u306e\u30c7\u30fc\u30bf\u54c1\u8cea\u306e\u91cd\u8981\u6027\u306f\u4ed6\u306e\u8ad6\u6587\u3067\u3082\u6307\u6458\u3055\u308c\u3066\u304a\u308a\uff08\u3086\u3048\u306bRLHF\u304c\u6709\u52b9\u3068\u3044\u3046\u8a71\u3082\u3042\u308a\uff09\u53c2\u8003\u306b\u306a\u308b\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/lichang-chen.github.io\/AlpaGasus\/\">AlpaGasus: Training a Better Alpaca with Fewer Data (lichang-chen.github.io)<\/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":[102,223],"class_list":["post-3589","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-dataset-distillation","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3589","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=3589"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3589\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3589"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3589"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3589"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}