Perplexity open-sources pplx-embed-v2-late multimodal late-interaction embedding models (9B and 0.6B)
Original title:We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can ...
AI summary
Perplexity open-sourced pplx-embed-v2-late, two late-interaction multi-vector embedding models for text and images, sized 9B and 0.6B, sharing the same embedding space, with weights available on Hugging Face. The 9B model can index multimodal data, while the 0.6B model can run queries on-device and retrieve PDF pages without OCR; the models score 92.4% on MADQA and 64% on BrowseComp+.
Key Takeaways
- Perplexity open-sourced pplx-embed-v2-late,two late-interaction multi-vector embedding models for…
- 6B,sharing the same embedding space,with weights available on Hugging Face.
- The 9B model can index multimodal data,while the 0.
- 6B model can run queries on-device and retrieve PDF pages without OCR
- the models score 92.
Quick Facts
- Published
- Updated
- Category
- Model Releases
- AI score
- 65
原文给出两个规模的嵌入模型、共享空间用法和基准分数,读者可据此评估多模态检索与端侧查询的可行方案。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Perplexity open-sources pplx-embed-v2-late multimodal late-interaction embedding models (9B and 0.6B). October 8, 2026. https://new.nat6.net/en/news/lfy2ww68p9lgpxxhu5jssflwf/