Perplexity 发布嵌入模型 pplx-embed-v2-late，含 0.6B 边缘版和 9B 版
Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA
Perplexity 出了开源嵌入模型，小的 0.6B 能跑在边缘设备上，大的 9B 在 MADQA 拿了 92.4%，MIT 协议可以自己部署。
Perplexity 发布嵌入模型 pplx-embed-v2-late，提供两个规格：0.6B 版本面向边缘设备运行，9B 版本用于构建高质量索引。在 MADQA 基准上最佳成绩为 92.4%，最弱成绩为 ViDoRe v3 Markdown 上的 61.2%。两个版本均采用 MIT 许可证，支持自托管部署。
Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA
Perplexity's pplx-embed-v2-late comes in 2 sizes: a 0.6B model built to run on edge devices, and a 9B model for building high-quality indexes. Its best score is 92.4% on MADQA, and its weakest is 61.2% on ViDoRe v3 Markdown. Both are MIT-licensed and ready to self-host. The post Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA appeared first on MarkTechPost .
- Aravind Srinivas10-07 16:33原文
