Sentence Transformers v6 released with focus on Multi-Vector Embedding Models
NielsRogge · x · 2026-08-18
Sentence Transformers v6 is released, centering on Multi-Vector Embedding Models.
Traditional semantic search uses "bi-encoders" (like OpenAI Embedding API), encoding documents and queries separately to compute cosine similarity. In 2020, Stanford researchers introduced ColBERT to improve this: it creates multiple vectors (token-level embeddings) for each document and query, matching them via a MaxSim operation to achieve more precise retrieval while maintaining efficiency.
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