{"id":4662,"date":"2024-04-08T05:54:00","date_gmt":"2024-04-07T20:54:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4662"},"modified":"2024-04-08T05:54:00","modified_gmt":"2024-04-07T20:54:00","slug":"cohere-command-r-aurora-m-hyperclova-x","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4662","title":{"rendered":"Cohere Command R+, AURORA-M, HyperCLOVA X, EURUS"},"content":{"rendered":"\n<p>\u5148\u9031\u3082LLM\u95a2\u9023\u306e\u8a71\u984c\u304c\u591a\u304b\u3063\u305f\u3002Cohere Command R+\u306fGPT-4\u76f8\u5f53\u3092\u3046\u305f\u3046104B\u306eLLM\u3067\u3042\u308a\u3001huggingface\u3067CC-BY-NC\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u3002\u5b8c\u5168\u306b\u5546\u7528\u30af\u30aa\u30ea\u30c6\u30a3\u306e\u30e2\u30c7\u30eb\u304c\u975e\u5546\u7528\u5229\u7528\u306e\u307f\u3068\u306f\u3044\u3048\u516c\u958b\u3055\u308c\u305f\u306e\u306f\u885d\u6483\u7684\u3060\u3063\u305f\u3002\u7814\u7a76\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u306b\u5bfe\u3059\u308b\u5927\u304d\u306a\u8ca2\u732e\u3060\u3068\u601d\u3046\u3002<\/p>\n\n\n\n<p>Aurora-M\u306fStarCoderPlus\u304b\u3089\u7d99\u7d9a\u5b66\u7fd2\u306b\u3088\u3063\u3066\u4f5c\u3089\u308c\u305f\u30aa\u30fc\u30d7\u30f3\u306aLLM\u3001HyperCLOVA X\u306fNAVER\u306b\u3088\u308b\u97d3\u56fd\u8a9e\u306b\u5f37\u3044LLM\u3067\u3042\u308b\u3002EURUS\u306a\u3069\u30aa\u30fc\u30d7\u30f3\u306aLLM\u3092\u5f37\u5316\u3057\u3088\u3046\u3068\u3044\u3046\u30c8\u30e9\u30a4\u3082\u591a\u3044\u3002<\/p>\n\n\n\n<p><strong>Introducing Command R+: A ScalableLLM Built for Business<\/strong><br>Command R+\u306f\u3001\u30a8\u30f3\u30bf\u30fc\u30d7\u30e9\u30a4\u30ba\u30b0\u30ec\u30fc\u30c9\u306e\u30ef\u30fc\u30af\u30ed\u30fc\u30c9\u306b\u53d6\u308a\u7d44\u3080\u305f\u3081\u306b\u8a2d\u8a08\u3055\u308c\u305f\u6700\u5148\u7aef\u306eRAG\u6700\u9069\u5316\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002\u6700\u521d\u306fmicrosoft azure\u3067\u5229\u7528\u53ef\u80fd\u3060\u3002<br><a href=\"https:\/\/txt.cohere.com\/command-r-plus-microsoft-azure\/\">Introducing Command R+: A Scalable LLM Built for Business (cohere.com)<\/a><br>Mistral Large\u4ee5\u4e0a\u3001GPT-4-Turbo\u76f8\u5f53\u3092\u4e3b\u5f35\u3059\u308bLLM\u3001\u5546\u7528\u5229\u7528\u4e0d\u53ef\u306e\u6761\u4ef6\u3067\u306f\u3042\u308b\u304c\u7814\u7a76\u7528\u306b\u4f7f\u7528\u53ef\u80fd\u306a\u30e2\u30c7\u30eb\u304c\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u306e\u304c\u3059\u3054\u3044<br>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/huggingface.co\/CohereForAI\/c4ai-command-r-plus\">CohereForAI\/c4ai-command-r-plus \u00b7 Hugging Face<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order&nbsp;<\/strong>[123.7]<br>Aurora-M\u306f\u3001\u82f1\u8a9e\u3001\u30d5\u30a3\u30f3\u30e9\u30f3\u30c9\u8a9e\u3001\u30d2\u30f3\u30c7\u30a3\u30fc\u8a9e\u3001\u65e5\u672c\u8a9e\u3001\u30d9\u30c8\u30ca\u30e0\u8a9e\u3001\u30b3\u30fc\u30c9\u3067\u8a13\u7df4\u3055\u308c\u305f15B\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u591a\u8a00\u8a9e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002 \u3053\u308c\u306f\u3001\u4eba\u9593\u304c\u30ec\u30d3\u30e5\u30fc\u3057\u305f\u5b89\u5168\u547d\u4ee4\u3092\u5fae\u8abf\u6574\u3057\u305f\u521d\u3081\u3066\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u591a\u8a00\u8a9e\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002 \u69d8\u3005\u306a\u30bf\u30b9\u30af\u3084\u8a00\u8a9e\u3067\u53b3\u683c\u306b\u8a55\u4fa1\u3055\u308c\u3066\u304a\u308a\u3001\u7834\u6ec5\u7684\u306a\u5fd8\u308c\u7269\u306b\u5bfe\u3059\u308b\u9811\u4e08\u3055\u3092\u793a\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2404.00399v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2404.00399v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Sat, 30 Mar 2024 15:38:54 GMT)<\/li>\n\n\n\n<li>15B\u306e\u30aa\u30fc\u30d7\u30f3\u306a\u591a\u8a00\u8a9eLLM\u3001\u6027\u80fd\u306fLlama2 13B\u3068\u7af6\u5408\u3068\u3044\u3046\u611f\u3058\u3067\u306f\u3042\u308b\u304c\u5b89\u5168\u6027\u306b\u975e\u5e38\u306b\u6c17\u3092\u4f7f\u3063\u305f\u30e2\u30c7\u30eb\u306b\u306a\u3063\u3066\u3044\u308b\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/huggingface.co\/collections\/aurora-m\/aurora-m-models-65fdfdff62471e09812f5407\">Aurora-M models &#8211; a aurora-m Collection (huggingface.co)<\/a><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>HyperCLOVA X Technical Report&nbsp;<\/strong>[119.1]<br>\u97d3\u56fd\u8a9e\u3068\u6587\u5316\u306b\u5408\u308f\u305b\u305f\u5927\u578b\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306e\u30d5\u30a1\u30df\u30ea\u30fc\u3067\u3042\u308bHyperCLOVA X\u3092\u7d39\u4ecb\u3059\u308b\u3002 HyperCLOVA X\u306f\u97d3\u56fd\u8a9e\u3001\u82f1\u8a9e\u3001\u30b3\u30fc\u30c9\u30c7\u30fc\u30bf\u306e\u30d0\u30e9\u30f3\u30b9\u306e\u53d6\u308c\u305f\u6df7\u5408\u3067\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3055\u308c\u3001\u305d\u306e\u5f8c\u3001\u9ad8\u54c1\u8cea\u306a\u4eba\u9593\u30a2\u30ce\u30c6\u30fc\u30b7\u30e7\u30f3\u4ed8\u304d\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u3088\u308b\u547d\u4ee4\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u304c\u884c\u308f\u308c\u305f\u3002 \u3053\u306e\u30e2\u30c7\u30eb\u306f\u3001\u97d3\u56fd\u8a9e\u3068\u82f1\u8a9e\u306e\u4e21\u65b9\u3067\u3001\u5305\u62ec\u7684\u306a\u63a8\u8ad6\u3001\u77e5\u8b58\u3001\u5e38\u8b58\u3001\u4e8b\u5b9f\u6027\u3001\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3001\u6570\u5b66\u3001\u30c1\u30e3\u30c3\u30c8\u3001\u6307\u793a\u8ffd\u5f93\u3001\u7121\u5bb3\u306a\u3069\u3001\u69d8\u3005\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u8a55\u4fa1\u3055\u308c\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2404.01954v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2404.01954v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Tue, 02 Apr 2024 13:48:49 GMT)<\/li>\n\n\n\n<li>NAVER\u306b\u3088\u308bLLM,\u97d3\u56fd\u8a9e\u80fd\u529b\u304c\u9ad8\u3044\u304c\u3001\u82f1\u8a9e\u3067\u3082Llama2 70B\u3068\u7af6\u3063\u3066\u304a\u308a\u80fd\u529b\u304c\u9ad8\u3044\u3002\u30d1\u30e9\u30e1\u30fc\u30bf\u6570\u306f\u975e\u516c\u8868\uff1f<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Advancing LLM Reasoning Generalists with Preference Trees&nbsp;<\/strong>[119.6]<br>\u63a8\u8ad6\u306b\u6700\u9069\u5316\u3055\u308c\u305f\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306e\u30b9\u30a4\u30fc\u30c8\u3067\u3042\u308bEulus\u3092\u7d39\u4ecb\u3059\u308b\u3002 Eurus\u30e2\u30c7\u30eb\u306f\u3001\u69d8\u3005\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306e\u30e2\u30c7\u30eb\u306e\u9593\u3067\u6700\u5148\u7aef\u306e\u7d50\u679c\u3092\u5f97\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2404.02078v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2404.02078v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Tue, 02 Apr 2024 16:25:30 GMT)<\/li>\n\n\n\n<li>Mistral-7B, CodeLlama-70B\u304b\u3089SFT\u3055\u308c\u305f\u30e2\u30c7\u30eb\u3001UltraInteract\u3068\u3044\u3046\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304c\u30b3\u30a2\u3002\u300cEURUS-70B beats GPT-3.5 Turbo in reasoning through a comprehensive benchmarking across 12 tests covering five tasks\u300d\u306f\u3059\u3054\u3044<\/li>\n\n\n\n<li><a href=\"https:\/\/github.com\/OpenBMB\/Eurus\">OpenBMB\/Eurus (github.com)<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u5148\u9031\u3082LLM\u95a2\u9023\u306e\u8a71\u984c\u304c\u591a\u304b\u3063\u305f\u3002Cohere Command R+\u306fGPT-4\u76f8\u5f53\u3092\u3046\u305f\u3046104B\u306eLLM\u3067\u3042\u308a\u3001huggingface\u3067CC-BY-NC\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u3002\u5b8c\u5168\u306b\u5546\u7528\u30af\u30aa\u30ea\u30c6\u30a3\u306e\u30e2\u30c7\u30eb\u304c\u975e\u5546\u7528\u5229\u7528\u306e\u307f\u3068 &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=4662\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;Cohere Command R+, AURORA-M, HyperCLOVA X, EURUS&#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":[223,293],"class_list":["post-4662","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-oss"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4662","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=4662"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4662\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4662"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4662"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4662"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}