STv6 released with native support for ColPali-style multimodal retrieval

IgorCarron · x · 2026-08-18

Sentence Transformers v6 (STv6) has been released, featuring out-of-the-box support for ColPali-style Vision Language Models (VLMs). The update unifies checkpoint loading via a single PyLate class, handling HFColBERT markers, ColPali-style VLMs, and bare backbones. Configurations for prefixes, query expansion, and punctuation skiplists are automatically restored. It also includes beloved features like token pooling and similarity maps for better interpretability.

Related event: Sentence Transformers v6.0 ships with first-class late interaction models(33 posts)→

Original post →

More from Models

Models channel →