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

MarkTechPost
Read the full article
Perplexity AI released pplx-embed-v2-late, two multimodal embedding models sized 0.6B and 9B parameters, capable of retrieving text, images, and PDFs in a shared embedding space. The 0.6B model suits edge devices with fast queries, while the 9B model offers higher accuracy, scoring 92.4% on MADQA. Both models are open-source on Hugging Face under the MIT license, with a hosted API planned.

More in Machine Learning

Meta Says New AI Model Is State-of-the-Art, Will Make Muse Agent Smarter

Covered by 2 sources
Machine Learning3 min read

Microsoft launches a decision model built on Alibaba’s Qwen

The Next Web
Machine Learning12 min read

Turning Opportunistic AI Inference Capacity Into Better Ads Recommendations

Meta AI News