{"id":3277,"date":"2023-05-03T05:56:00","date_gmt":"2023-05-02T20:56:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3277"},"modified":"2023-05-03T05:56:00","modified_gmt":"2023-05-02T20:56:00","slug":"wizardlm","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3277","title":{"rendered":"WizardLM"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>WizardLM: Empowering Large Language Models to Follow Complex Instructions&nbsp;<\/strong>[67.4]<br>\u30d2\u30c8\u306e\u4ee3\u308f\u308a\u306b\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u3092\u7528\u3044\u3066\u3001\u69d8\u3005\u306a\u30ec\u30d9\u30eb\u306e\u8907\u96d1\u3055\u3092\u6301\u3064\u5927\u91cf\u306e\u547d\u4ee4\u30c7\u30fc\u30bf\u3092\u4f5c\u6210\u3059\u308b\u65b9\u6cd5\u3092\u793a\u3059\u3002 \u6211\u3005\u306f\u63d0\u6848\u3057\u305fEvol-Instruct\u3092\u4f7f\u3063\u3066\u3001\u3088\u308a\u8907\u96d1\u306a\u547d\u4ee4\u3068\u5fae\u8abf\u6574\u306eLLaMA\u3092\u6bb5\u968e\u7684\u306b\u66f8\u304d\u76f4\u3059\u3002 \u8907\u96d1\u6027\u30d0\u30e9\u30f3\u30b9\u30c6\u30b9\u30c8\u30d9\u30c3\u30c9\u4e0a\u3067\u306e\u4eba\u9593\u8a55\u4fa1\u306f\u3001Evol-Instruct\u304b\u3089\u306e\u6307\u793a\u304c\u4eba\u9593\u304c\u4f5c\u3063\u305f\u3082\u306e\u3088\u308a\u3082\u512a\u308c\u3066\u3044\u308b\u3053\u3068\u3092\u793a\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.12244v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.12244v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Mon, 24 Apr 2023 16:31:06 GMT)<\/li>\n\n\n\n<li>\u73fe\u5b9f\u554f\u984c\u3068\u3057\u3066\u898f\u7d04\u7684\u306b\u3067\u304d\u306a\u3044\u5834\u5408\u306f\u3042\u308b\u304c\u3001LLM\u3092\u7528\u3044\u305f&nbsp;instruction data\u306e\u4f5c\u6210\u3002\u69d8\u3005\u306a\u8907\u96d1\u3055\u306e\u30c7\u30fc\u30bf\u3092\u4f5c\u308c\u308b\u306e\u304c\u7279\u5fb4\u3068\u306e\u3053\u3068\u3002\u4f5c\u6210\u3057\u305f\u30c7\u30fc\u30bf\uff0bLLaMA\u3067\u4f5c\u3063\u305f\u30e2\u30c7\u30eb\u306fAlpaca\u3001Vicuna\u3088\u308a\u512a\u308c\u3066\u3044\u308b\u3088\u3046\u306b\u898b\u3048\u308b\u304cChatGPT\u306b\u306f\u53ca\u3093\u3067\u3044\u306a\u3055\u305d\u3046\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/nlpxucan\/WizardLM\">GitHub &#8211; nlpxucan\/WizardLM: WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions<\/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":[63],"class_list":["post-3277","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-chatgpt"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3277","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=3277"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3277\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3277"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3277"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3277"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}