{"id":1248,"date":"2021-12-27T05:00:00","date_gmt":"2021-12-26T20:00:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=1248"},"modified":"2021-12-27T05:00:00","modified_gmt":"2021-12-26T20:00:00","slug":"ernie-3-0-titan-the-largest-chinese-dense-pre-trained-model","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=1248","title":{"rendered":"ERNIE 3.0 Titan: the largest Chinese dense pre-trained model"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation\u00a0<\/strong>[50.0]<br>GPT-3\u306f\u3001\u4e8b\u524d\u8a13\u7df4\u3055\u308c\u305f\u8a00\u8a9e\u30e2\u30c7\u30eb\u3092\u30b9\u30b1\u30fc\u30eb\u30a2\u30c3\u30d7\u3059\u308b\u3053\u3068\u3067\u3001\u305d\u306e\u6f5c\u5728\u80fd\u529b\u3092\u3055\u3089\u306b\u6d3b\u7528\u3067\u304d\u308b\u3053\u3068\u3092\u793a\u3057\u305f\u3002\u00a0ERNIE 3.0\u306e\u30b9\u30b1\u30fc\u30eb\u30a2\u30c3\u30d7\u6027\u80fd\u3092\u8abf\u3079\u308b\u305f\u3081\u3001PaddlePaddle\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0\u4e0a\u3067\u6700\u59272600\u5104\u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u6301\u3064ERNIE 3.0 Titan\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3001\u69d8\u3005\u306aNLP\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u6700\u5148\u7aef\u306e\u30e2\u30c7\u30eb\u3088\u308a\u3082\u512a\u308c\u3066\u3044\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2112.12731v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2112.12731v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 23 Dec 2021 17:35:48 GMT)<ul><li>Baidu\u306e\u5de8\u5927\u8a00\u8a9e\u30e2\u30c7\u30eb\u300168\u306eNLP\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067SoTA\u3068\u306e\u3053\u3068\u3002<\/li><li>\u5b66\u7fd2\u3092GPU\u3068Ascend 910\u3092\u4f75\u7528\u3057\u30d8\u30c6\u30ed\u30b8\u30cb\u30a2\u30b9\u306a\u69cb\u6210\u3067\u884c\u3046\u3001\u63a8\u8ad6\u3082Nvidia A100-SXM4(40GB)\u3067\u306f\u4e0d\u53ef\u80fd\u3067\u5206\u6563\u5b9f\u65bd\u3068\u30a4\u30f3\u30d5\u30e9\u90e8\u5206\u3082\u8208\u5473\u6d25\u3005<\/li><\/ul><ul><li>\u4e00\u5ea6\u306b\u8907\u6570\u306e\u751f\u5f92\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u53ef\u80fd\u306aOnline Distillation Framework\u3092\u63d0\u6848\u3057\u3066\u3044\u308b\u306e\u3082\u8208\u5473\u6df1\u3044<\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generat &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=1248\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;ERNIE 3.0 Titan: the largest Chinese dense pre-trained model&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[170,287,567,635],"class_list":["post-1248","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-gigantic-language-model","tag-online-distillation","tag-567","tag-635"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1248","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=1248"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1248\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1248"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1248"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1248"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}