{"id":4224,"date":"2024-01-01T05:24:00","date_gmt":"2023-12-31T20:24:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4224"},"modified":"2024-01-01T05:24:00","modified_gmt":"2023-12-31T20:24:00","slug":"yayi-2","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4224","title":{"rendered":"YAYI 2"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>YAYI 2: Multilingual Open-Source Large Language Models\u00a0<\/strong>[53.9]<br>\u6211\u3005\u306f,300\u5104\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u6301\u3064\u30d9\u30fc\u30b9\u30e2\u30c7\u30eb\u3068\u30c1\u30e3\u30c3\u30c8\u30e2\u30c7\u30eb\u3092\u542b\u3080YAYI 2\u3092\u63d0\u6848\u3059\u308b\u3002 YAYI 2\u306f\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u6e08\u307f\u306e\u30c7\u30fc\u30bf\u51e6\u7406\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u306b\u3088\u3063\u3066\u30d5\u30a3\u30eb\u30bf\u3055\u308c\u305f2.65\u5146\u306e\u30c8\u30fc\u30af\u30f3\u3092\u542b\u3080\u591a\u8a00\u8a9e\u30b3\u30fc\u30d1\u30b9\u4e0a\u3067\u3001\u30b9\u30af\u30e9\u30c3\u30c1\u304b\u3089\u4e8b\u524d\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3055\u308c\u308b\u3002 \u30d9\u30fc\u30b9\u30e2\u30c7\u30eb\u306f\u3001\u6570\u767e\u4e07\u306e\u6307\u793a\u306b\u3088\u308b\u6559\u5e2b\u4ed8\u304d\u5fae\u8abf\u6574\u3068\u3001\u4eba\u9593\u306e\u30d5\u30a3\u30fc\u30c9\u30d0\u30c3\u30af\u304b\u3089\u306e\u5f37\u5316\u5b66\u7fd2\u306b\u3088\u3063\u3066\u3001\u4eba\u9593\u306e\u4fa1\u5024\u3068\u6574\u5408\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2312.14862v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2312.14862v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 22 Dec 2023 17:34:47 GMT)<\/li>\n\n\n\n<li>\u591a\u8a00\u8a9e\u5bfe\u5fdc\u304b\u3064\u9ad8\u6027\u80fd\u306aLLM YAYI2\u306e\u8ad6\u6587\u3002YAYI2 30B\u306f5 shot\u306eMMLU\u3067Score=80.5\u3068\u9ad8\u3044\u3002\u5b66\u7fd2\u30c7\u30fc\u30bf\u306e\u30af\u30ec\u30f3\u30b8\u30f3\u30b0\u304b\u3089pre train, SFT, RLHF\u3068\u69cb\u7bc9\u904e\u7a0b\u3082\u975e\u5e38\u306b\u53c2\u8003\u306b\u306a\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/wenge-research\/YAYI2\/blob\/main\/README_EN.md\">YAYI2\/README_EN.md at main \u00b7 wenge-research\/YAYI2 (github.com<\/a>\u3001\u30b3\u30fc\u30c9\u306fOSS\u306e\u3088\u3046\u3060\u304cweight\u306f\u5225\u9014\u30e9\u30a4\u30bb\u30f3\u30b9\u304c\u5b9a\u3081\u3089\u308c\u3066\u3044\u308b\u70b9\u306b\u6ce8\u610f\u3002<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>YAYI-UIE: A Chat-Enhanced Instruction Tuning Framework for Universal Information Extraction\u00a0<\/strong>[21.0]<br>\u30e6\u30cb\u30d0\u30fc\u30b5\u30eb\u60c5\u5831\u62bd\u51fa(YAYI-UIE)\u306e\u305f\u3081\u306e\u30a8\u30f3\u30c9\u30c4\u30fc\u30a8\u30f3\u30c9\u306e\u30c1\u30e3\u30c3\u30c8\u5f37\u5316\u6307\u5c0e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u63d0\u6848\u3059\u308b\u3002 \u5177\u4f53\u7684\u306b\u306f,\u5bfe\u8a71\u30c7\u30fc\u30bf\u3068\u60c5\u5831\u62bd\u51fa\u30c7\u30fc\u30bf\u3092\u7528\u3044\u3066,\u60c5\u5831\u62bd\u51fa\u6027\u80fd\u3092\u5354\u8abf\u7684\u306b\u5411\u4e0a\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2312.15548v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2312.15548v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sun, 24 Dec 2023 21:33:03 GMT)<\/li>\n\n\n\n<li>\u95a2\u9023\u3057\u3066universal information extraction task\u3078\u306e\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u624b\u6cd5\u3001<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/wenge-research\/YAYI-UIE\/blob\/main\/README_EN.md\">YAYI-UIE\/README_EN.md at main \u00b7 wenge-research\/YAYI-UIE (github.com)<\/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":[223,267],"class_list":["post-4224","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-multilingual"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4224","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=4224"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4224\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4224"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4224"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4224"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}