Sentence Transformers 6.2.0 cuts training memory with quadratic/linear loss storage
tomaarsen · x · 2026-10-21
Sentence Transformers 6.2.0 reduces training memory: BatchSemiHardTripletLoss intermediate memory drops from cubic to quadratic, BatchAllTripletLoss to quadratic for paired labels, and CoSENTLoss/AnglELoss (including sparse variants) now use linear intermediate storage. Large BatchAll label groups can still be cubic.
More from coding & agent
- Three ways to let Claude Opus 5.5 click around your computer: cua-driver, OpenAI CUA MCP, or OSWorld harness — zsakib_ · 2026-10-21
- REUF2F Benchmarks Coding Agents on Formalized Undergraduate Research Problems — wellecks · 2026-10-21
- At NVIDIA GTC Berlin, OpenClaw Drives a Full Robotic Simulation on a Single DGX Spark — vincent_koc · 2026-10-21
- US healthtech deploys AI agents to collect patient bills, paid only on recovery — alex_verem · 2026-10-21
- Where should market agents stop? Default to monitoring, require approval to act — Decent_Wing_4393 · 2026-10-21
- Testing Codex × CapCut Web: turning a brand campaign brief into video via natural language — Div_pradeep · 2026-10-21