{"id":5022,"date":"2024-03-07T09:33:31","date_gmt":"2024-03-07T01:33:31","guid":{"rendered":"https:\/\/www.1ai.net\/?p=5022"},"modified":"2024-03-07T09:33:31","modified_gmt":"2024-03-07T01:33:31","slug":"%e6%9d%8e%e5%bc%80%e5%a4%8d%e6%97%97%e4%b8%8b-ai-%e5%85%ac%e5%8f%b8%e9%9b%b6%e4%b8%80%e4%b8%87%e7%89%a9%e5%ae%a3%e5%b8%83%e5%bc%80%e6%ba%90-yi-9b-%e6%a8%a1%e5%9e%8b%ef%bc%8c%e5%8f%b7%e7%a7%b0%e5%90%8c","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/5022.html","title":{"rendered":"Kai-Fu Lee's AI company Zero One Everything announced the open source Yi-9B model, claiming to have the strongest mathematical capabilities in the same series of codes"},"content":{"rendered":"

\u201cZero One Everything<\/a> 01AI" official WeChat account announced tonightOpen Source Yi-9B Model<\/a>, officially called the Yi seriesModel<\/a>The "Science Champion" in the series - Yi-9B is the model with the strongest code and mathematical capabilities in the current Yi series models.Reality<\/span>The actual parameter is 8.8B, and the default context length is 4K tokens.<\/span>.<\/p>\n

\"\"<\/p>\n

This model is based on Yi-6B (trained with 3.1T tokens) and uses 0.8T tokens for further training. The data is as of June 2023.<\/p>\n

According to reports, in terms of comprehensive ability (Mean-All),Yi-9B's performance is "better than other similar sizedOpen Source<\/a>The best model<\/span>, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B and Gemma-7B.<\/p>\n

In terms of coding capability (Mean-Code), Yi-9B\u2019s performance is second only to DeepSeek-Coder-7B, and surpasses Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B.<\/p>\n

In terms of mathematical capabilities (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, and surpasses SOLAR-10.7B, Mistral-7B, and Gemma-7B.<\/p>\n

In terms of common sense and reasoning ability (Mean-Text), Yi-9B performs on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B.<\/p>\n

The official said,Yi-9B (BF 16) and its quantized version Yi-9B (Int8) can be easily deployed on consumer-grade graphics cards<\/span>, low cost of use and developer-friendly.<\/p>\n

\"\"<\/p>\n

The companyKai-Fu Lee<\/a>The chairman and CEO of Sinovation Ventures led the team to found the company, which has already launched two models, Yi-34B and Yi-6B.Open Source Big Model<\/a>, claiming to be completely open to academic research and simultaneously open to free commercial applications.<\/p>","protected":false},"excerpt":{"rendered":"

The official public number of \"01AI\" announced tonight that it has open-sourced the Yi-9B model, which is officially called the \"top science\" model in the Yi series - Yi-9B is the most powerful model in terms of code and math among the current Yi series models. Yi-9B is the model with the strongest code and mathematical ability among the current Yi series models, with actual parameters of 8.8B and a default context length of 4K tokens. The model is based on Yi-6B (which was trained with 3.1T tokens), and continues to be trained with 0.8T tokens, and the data is up to June 2023,\" said the official public post of Yi-9B. In terms of overall capability (Mean-All), Yi-9B is described as having the \"best performance among similarly sized open-source models\", outperforming the DeepSeek-Code<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[219,391,1518,1489,1519],"collection":[],"class_list":["post-5022","post","type-post","status-publish","format-standard","hentry","category-news","tag-219","tag-391","tag-1518","tag-1489","tag-1519"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/5022","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=5022"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/5022\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=5022"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=5022"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=5022"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=5022"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}