AI News

Perplexity 开源 Decider v1.3 与 Decider Flash v1.3 决策模型

Aravind Srinivas更新于 11月13日 07:45

We're open-sourcing our latest versions of Decision Models: Decider v1.3 and Decider Flash v1.3, and making them free on @OpenRouter for a week.

AI 导读

Perplexity 开源 Decider v1.3 和 Decider Flash v1.3 两个决策模型,并在 OpenRouter 上免费开放一周。v1.3 新增 locate 能力,可按描述返回匹配文本及字符偏移,适用于批量决策与证据、实体抽取。官方称在 17 个域外 NER、PII 和抽取式 QA 任务上明显优于最好的通用抽取模型,在自家 63 个生产分类任务上比现用分类器准确率高 6.54 个百分点,权重已发布于 Hugging Face。

推荐理由

AI 评分 58

原文给出了新版本的开源权重、免费试用入口和两类任务上的对比数据,可据此判断抽取类任务是否值得迁移。

主题

标签

引用

Perplexity Developers

@perplexitydevs

我们正在推出 pplx-decider-v1.3 和 pplx-decider-flash-v1.3,这是我们开放权重决策模型的最新版本。 v1.3 新增了 locate,这是一项新功能,可根据类型或指令提取文本片段。 现已在我们的 Decisions API、@huggingface 和 @OpenRouter 上提供。 https://t.co/bsTSl2tHSo

查看原文

We're rolling out pplx-decider-v1.3 and pplx-decider-flash-v1.3, the latest version of our open-weight decision models. v1.3 adds locate, a new feature that extracts spans based on type or instructions. Now available in our Decisions API, @huggingface, and @OpenRouter. https://t.co/bsTSl2tHSo

查看原帖

正文

We're open-sourcing our latest versions of Decision Models: Decider v1.3 and Decider Flash v1.3, and making them free on @OpenRouter for a week.

The new capability in v1.3 models is "locate". This lets you describe what to find, and the model returns the matching text with character offsets.

This is useful for batch-mode decision + evidence/entity extraction. On 17 out-of-domain NER, PII and extractive QA tasks, Decider models significantly outperform the best general extraction model.

And, on 63 of our own production classification tasks, v1.3 is 6.54 points more accurate than the classifiers we run today.

Weights are open on Hugging Face: https://t.co/6olEOrOq4y

来源

Aravind Srinivas