{"id":19373,"date":"2024-09-05T09:39:49","date_gmt":"2024-09-05T01:39:49","guid":{"rendered":"https:\/\/www.1ai.net\/?p=19373"},"modified":"2024-09-05T09:39:49","modified_gmt":"2024-09-05T01:39:49","slug":"%e9%9b%b6%e4%b8%80%e4%b8%87%e7%89%a9%e5%bc%80%e6%ba%90-yi-coder-%e7%b3%bb%e5%88%97%e7%bc%96%e7%a8%8b%e5%8a%a9%e6%89%8b%e6%a8%a1%e5%9e%8b%ef%bc%8c%e6%94%af%e6%8c%81-52-%e7%a7%8d%e7%bc%96%e7%a8%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/19373.html","title":{"rendered":"Zero One Everything opens source Yi-Coder series programming assistant models, supporting 52 programming languages"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%9b%b6%e4%b8%80%e4%b8%87%e7%89%a9\" title=\"[Sees articles with labels]\" target=\"_blank\" >Zero One Everything<\/a>Announced today<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a>\u00a0Y<strong>i-Coder series models,<\/strong>This model is one of the Yi series models<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e7%bc%96%e7%a8%8b%e5%8a%a9%e6%89%8b\" title=\"_Other Organiser\" target=\"_blank\" >Programming Assistant<\/a>.<\/p>\n<p>The Yi-Coder series of models are designed for coding tasks.<strong>Two parameters are available: 1.5B and 9B.<\/strong>Among them, Yi-Coder-9B\u2019s performance is said to be \u201cbetter than other models with parameters below 10B\u201d, such as CodeQwen1.5 7B and CodeGeex4 9B, and can even be \u201ccomparable to DeepSeek-Coder 33B\u201d.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-19374\" title=\"bea00c23j00sjbgbf001od000hz00mbm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/bea00c23j00sjbgbf001od000hz00mbm.jpg\" alt=\"bea00c23j00sjbgbf001od000hz00mbm\" width=\"647\" height=\"803\" \/><\/p>\n<p>&nbsp;<\/p>\n<p>It is reported that Yi-Coder can handle up to 1<strong>28K tokens of context,<\/strong>Suitable for understanding and generating complex project-level codes. Yi-Coder also supports 52 major programming languages.<\/p>\n<p>`java ' , `markdown ' , `phython ' , `java ' , `c+ ' , `c# ' , `c ' , `ype ' , `html ', 'go ' , `java_pages ', `dart ' , `objective-c ' , `kotlin ' , tx ', `sql ' , `ruby ' , `rust ' , `roustman ' , `cs ' , `yaml ' , `matlab ' , `jets ' , `g ' , `scal ' , `scalk ' , `scark ' , `m , `scarts ' , `m , `m' , `m , `g , `g' , uli uli , q , uli ,<\/p>\n<p>According to the official test of Zero One Everything, the pass rates of Yi-Coder-9B-Chat in HumanEval and MBPP reached 85.4% and 73.8% respectively. In addition, the accuracy of Yi-Coder 9B in CRUXEval-O reached more than 50% for the first time among open source Coder models.<\/p>\n<p>Yi-Coder is also strong in code editing and completion capabilities, and achieved excellent results in the CodeEditorBench evaluation. In terms of long sequence modeling and mathematical reasoning capabilities, Yi-Coder also demonstrated strong performance, whether in long text understanding or mathematical problem solving.<\/p>\n<p><strong>Project address:<\/strong>https:\/\/github.com\/01-ai\/Yi-Coder<\/p>","protected":false},"excerpt":{"rendered":"<p>Zero One Everything today announced the open source of the Yi-Coder Series of models, the programming assistant in the Yi Series family of models. Yi-Coder series models are designed for coding tasks and are available in 1.5B and 9B parameters. Among them, Yi-Coder-9B is claimed to \"outperform other models with up to 10B parameters\" such as CodeQwen1.5 7B and CodeGeex4 9B, and even \"rival DeepSeek-Coder 33B! \".   Yi-Coder is said to be able to handle up to 128K tokens of contextual content, making it suitable for understanding and generating complex project-level code. yi-Coder<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[219,2346,1519],"collection":[],"class_list":["post-19373","post","type-post","status-publish","format-standard","hentry","category-news","tag-219","tag-2346","tag-1519"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/19373","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=19373"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/19373\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=19373"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=19373"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=19373"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=19373"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}