{"id":4742,"date":"2024-04-25T05:23:00","date_gmt":"2024-04-24T20:23:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4742"},"modified":"2024-04-25T05:23:00","modified_gmt":"2024-04-24T20:23:00","slug":"jetmoe-reaching-llama2-performance-with-0-1m-dollars","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4742","title":{"rendered":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>JetMoE: Reaching Llama2 Performance with 0.1M Dollars\u00a0<\/strong>[25.3]<br>\u3053\u306e\u30ec\u30dd\u30fc\u30c8\u3067\u306f\u3001JetMoE-8B\u3068\u3044\u3046\u65b0\u3057\u3044\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u4f4e\u30b3\u30b9\u30c8\u306b\u3082\u304b\u304b\u308f\u3089\u305a\u3001JetMoE-8B\u306fLlama2-7B\u30e2\u30c7\u30eb\u3088\u308a\u512a\u308c\u3001JetMoE-8B-Chat\u306fLlama2-13B-Chat\u30e2\u30c7\u30eb\u3088\u308a\u512a\u308c\u3066\u3044\u305f\u3002 \u672c\u5831\u544a\u3067\u306f,\u3059\u3079\u3066\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30d1\u30e9\u30e1\u30fc\u30bf\u3068\u30c7\u30fc\u30bf\u6df7\u5408\u7269\u306b\u3064\u3044\u3066\u8a73\u8ff0\u3057,\u30aa\u30fc\u30d7\u30f3\u30d5\u30a1\u30f3\u30c7\u30fc\u30b7\u30e7\u30f3\u30e2\u30c7\u30eb\u306e\u958b\u767a\u306b\u304a\u3051\u308b\u4eca\u5f8c\u306e\u53d6\u308a\u7d44\u307f\u3092\u4fc3\u9032\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2404.07413v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2404.07413v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 11 Apr 2024 00:52:39 GMT)<\/li>\n\n\n\n<li>\u5b89\u4fa1\uff08\u3068\u3044\u3063\u3066\u3082\u300c$0.1 million, using 1.25T tokens from carefully mixed open-source corpora and 30,000 H100 GPU hours.\u300d\uff09\u3067LLM\u3092\u69cb\u7bc9\u3059\u308b\u30ec\u30b7\u30d4\u306e\u63d0\u6848<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/myshell-ai\/JetMoE\">myshell-ai\/JetMoE: Reaching LLaMA2 Performance with 0.1M Dollars (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":[223,551],"class_list":["post-4742","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-551"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4742","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=4742"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4742\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4742"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4742"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4742"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}