今天,我们发布了d1.2和d1.2-ultra,这是最先进的多模态决策模型。d1.2和d1.2-ultra都具备新的输出能力,能够处理文本、图像和音频。
> #1 on the @ArtificialAnlys Decision Index (75)
> 从输入中读取一个值(文本、数字或日期)
> 在文本中找到每段具有某种类型的文本(段落)1/ 🧵
> #1 on the @ArtificialAnlys Decision Index (75)
> 从输入中读取一个值(文本、数字或日期)
> 在文本中找到每段具有某种类型的文本(段落)1/ 🧵
查看原文
原帖正文
Today, we release d1.2 and d1.2-ultra, the state-of-the-art omnimodal decision models. d1.2 and d1.2-ultra both can process text, images, and audio with new output capabilities.> #1 on the @ArtificialAnlys Decision Index (75)
> Read a value from the input (text, number or date)
> Find every passage of a kind in a text (spans)
> Locate things in a picture (box for one, boxes for every instance)
> Estimate a number (number with a range)
> Pick every option that applies (choice)1/ 🧵
> Read a value from the input (text, number or date)
> Find every passage of a kind in a text (spans)
> Locate things in a picture (box for one, boxes for every instance)
> Estimate a number (number with a range)
> Pick every option that applies (choice)1/ 🧵
引用自 X
原帖地址:https://x.com/i/status/2122346077231923698
原帖:
本站媒体副本
0 条评论
登录后可以参与讨论。
成员登录还没有评论。第一条认真回应会很重要。