Medical retrieval model trained on RTX 3090 rivals full dataset runs
tomaarsen · x · 2026-08-26
Tomaarsen released the mLateOn-medical model and a detailed blog post. Scaling experiments revealed that training 100k pairs for 75 minutes on an RTX 3090 achieves within 1.2 NDCG@10 points of the full million-pair run. The model utilizes Multi-Vector Encoder and shows strong performance on medical retrieval benchmarks.
Related event: Fine-tuning ColBERT on a single RTX 3090 beats general-purpose retrievers(14 posts)→
More from Apps
- He built an interactive AI cartoon storybook of his nephew's first soccer match as a gift — Travi3000 · 2026-10-16
- Playable 3D web app explains how Perseverance landed on Mars autonomously — techartist_ · 2026-10-16
- Proto consolidates scattered Excel sheets and runs operations with AI agents — cneuralnetwork · 2026-10-16
- Dia AI browser officially launches on Windows — charliedeets · 2026-10-16
- Gemini Canvas workflow: turn a photo with measurements into an interactive 3D CAD studio exporting STLs — GeminiApp · 2026-10-16
- Self Labs launches Agent Vault to let AI agents log in and pay with credit cards — EXM7777 · 2026-10-16