{"id":9671,"date":"2024-05-04T12:18:30","date_gmt":"2024-05-04T04:18:30","guid":{"rendered":"https:\/\/www.1ai.net\/?p=9671"},"modified":"2024-05-04T12:18:30","modified_gmt":"2024-05-04T04:18:30","slug":"%e9%9d%a2%e5%a3%81%e6%99%ba%e8%83%bd%e5%8f%91%e5%b8%83-eurux-8x22b-%e5%bc%80%e6%ba%90%e5%a4%a7%e6%a8%a1%e5%9e%8b%ef%bc%9a%e4%bb%a3%e7%a0%81%e6%80%a7%e8%83%bd%e8%b6%85%e8%b6%8a-llama3-70b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/9671.html","title":{"rendered":"Mianbi Intelligent Releases Eurux-8x22B Open Source Large Model: Code Performance Exceeds Llama3-70B"},"content":{"rendered":"<p data-vmark=\"9dd7\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%9d%a2%e5%a3%81%e6%99%ba%e8%83%bd\" title=\"[View articles tagged with [face smart]]\" target=\"_blank\" >Wall-facing intelligence<\/a>release<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[Sees articles with labels]\" target=\"_blank\" >Open Source Big Model<\/a> Eurux-8x22B, including Eurux-8x22B-NCA and Eurux-8x22B-KTO, focuses on inference capability.<\/p>\n<p data-vmark=\"cfd7\">Eurux-8x22B in official tests\u00a0<span class=\"accentTextColor\">Tested on LeetCode (180 LeetCode programming questions) and TheoremQA (IT Home Note: U.S. college-level STEM questions).<\/span>first (of multiple parts)<span class=\"accentTextColor\">Outperforms Llama3-70B and outperforms closed-source GPT-3.5-Turbo on LeetCode tests.<\/span><\/p>\n<p data-vmark=\"594d\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-9672\" title=\"3fd0b648-83ec-4d49-ad19-c4aa5f9ad84c\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/05\/3fd0b648-83ec-4d49-ad19-c4aa5f9ad84c.png\" alt=\"3fd0b648-83ec-4d49-ad19-c4aa5f9ad84c\" width=\"1440\" height=\"962\" \/><\/p>\n<p data-vmark=\"20cd\">According to the introduction,<span class=\"accentTextColor\">Eurux-8x22B model activation parameter 39B, supports 64k contexts<\/span>, which is aligned from the Mixtral-8x22B model, trained on the UltraInteract aligned dataset.<\/p>\n<p data-vmark=\"8d11\">UltraInteract is a large-scale, high-quality alignment dataset designed specifically to improve large model inference, containing 86K instructions and 220K preference pairs from 12 open-source datasets covering mathematical, coding, and logical inference problems, for a total of half a million or so numbers of<\/p>","protected":false},"excerpt":{"rendered":"<p>Facade Intelligence released open source big models Eurux-8x22B, including Eurux-8x22B-NCA and Eurux-8x22B-KTO, focusing on reasoning ability. In official tests, Eurux-8x22B outperforms Llama3-70B on the LeetCode (180 LeetCode programming questions) and TheoremQA (IT House note: U.S. college-level STEM questions) tests, and outperforms closed-source GPT-3.5-Turbo on the LeetCode test. According to the report. Eurux-8x22B model with 39B activation parameters and 64k context support was developed by Mixtral-8x22B.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[391,2184],"collection":[],"class_list":["post-9671","post","type-post","status-publish","format-standard","hentry","category-news","tag-391","tag-2184"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/9671","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=9671"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/9671\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=9671"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=9671"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=9671"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=9671"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}