{"id":23948,"date":"2024-11-28T00:38:29","date_gmt":"2024-11-27T16:38:29","guid":{"rendered":"https:\/\/www.1ai.net\/?p=23948"},"modified":"2024-11-27T20:40:57","modified_gmt":"2024-11-27T12:40:57","slug":"%e6%98%86%e4%bb%91%e4%b8%87%e7%bb%b4%e5%a4%a9%e5%b7%a5%e5%a4%a7%e6%a8%a1%e5%9e%8b-4-0o1-%e7%89%88%e5%90%af%e5%8a%a8%e9%82%80%e6%b5%8b%ef%bc%8c%e5%85%b7%e5%a4%87%e4%b8%ad%e6%96%87","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/23948.html","title":{"rendered":"Kunlun World Wide \"Tiangong Da Model 4.0\" o1 Version Launches Invitation Test with Chinese Logical Reasoning Ability"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%98%86%e4%bb%91%e4%b8%87%e7%bb%b4\" title=\"[Sees articles with [Konlen] tags]\" target=\"_blank\" >Kunlun Wanwei<\/a>The Group announced on November 27 that it has officially launched a series of models with complex thinking and reasoning capabilities -- \"<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%a9%e5%b7%a5%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[Sees articles with labels]\" target=\"_blank\" >Tiangong Model<\/a> Version 4.0 \"o1 (Skywork o1).<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-23949\" title=\"615aa52fj00snm0ie0016d000tq00f3p\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/11\/615aa52fj00snm0ie0016d000tq00f3p.jpg\" alt=\"615aa52fj00snm0ie0016d000tq00f3p\" width=\"1070\" height=\"543\" \/><\/p>\n<p>According to the introduction, Skywork o1 is released by Kunlun Wanwei Group with \"<strong>slow thinking and reasoning<\/strong>\"The series of models, the first in the country<strong>Ability to reason logically in Chinese<\/strong>of the o1 model. Unlike existing efforts to reproduce OpenAI o1 models, Skywork o1 not only endogenizes the ability to think, plan, and reflect on model outputs, but also dramatically increases the ability to reason compared to ordinary models on standard evaluation sets, giving the model a<strong>Improvement in reasoning skills as a result of thought and reflection<\/strong>.<\/p>\n<p>The three models attached to this release are as follows:<\/p>\n<ul>\n<li><strong>Skywork o1 Open:<\/strong>An open source model based on Llama 3.1 8B , the model in the same ecological position in the open-source model of the review indicators significantly improved to the SOTA level , and unlocked many lightweight models can not solve the complex mathematical tasks . (Open source address:<a href=\"https:\/\/tinyurl.com\/skywork-o1\">Click here to go<\/a>\uff09<\/li>\n<li><strong>Skywork o1 Lite:<\/strong>The model has complete thinking capabilities with better Chinese language support and faster reasoning and thinking. It excels in math, Chinese logic and reasoning type problems.<\/li>\n<li><strong>Skywork o1 Preview:<\/strong>This is the full version of the reasoning model, with self-developed online reasoning algorithms, which provides a more varied and \"deeper\" thinking process, better and higher quality reasoning than Skywork o1 Lite.<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>On November 27th, Kunlun World Wide Group announced the official launch of Skywork o1, a series of models with complex thinking and reasoning ability. According to the introduction, Skywork o1 is a series of models with \"slow thinking and reasoning ability\" released by Kunlun World Wide Group, and it is the first o1 model with Chinese logical reasoning ability in China. Different from the existing work of reproducing OpenAI o1 models, Skywork o1 not only endogenizes the ability of thinking, planning and reflecting in the model output, but also increases the reasoning ability significantly compared to the ordinary models in the standard evaluation set, so that the model possesses the improved reasoning ability brought by thinking and reflecting. The three models attached to this release are as follows: Skywor<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[4955,1050],"collection":[],"class_list":["post-23948","post","type-post","status-publish","format-standard","hentry","category-news","tag-4955","tag-1050"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/23948","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=23948"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/23948\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=23948"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=23948"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=23948"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=23948"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}