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.
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16