aiqbench takeAI Products

Perplexity has released two new embedding models, pplx-embed-v2-late, optimized for edge deployment and high-fidelity indexing respectively. The smaller 0.6B variant targets resource-constrained environments, while the larger 9B model achieves a 92.4% score on the MADQA benchmark, offering developers flexible options for self-hosted RAG pipelines under an MIT license.

Source coveringMarkTechPost

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA

MarkTechPostOctober 8, 20261 min read

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.

Read the full article at MarkTechPost

Read at MarkTechPost ↗Ask about this article