Fine-tune ColBERT on one RTX 3090 to beat general-purpose retrievers
lateinteraction · x · 2026-08-26
A new blog post details training and finetuning multi-vector embedding models. As a practical example, the author finetuned a ColBERT-style model for medical retrieval on a single RTX 3090 in 14.5 hours, beating every general-purpose retriever found.
More from Research
- PrimeIntellect verifiers v0.3.1: Model Interception and Persistent ACP Sessions — xeophon · 2026-08-27
- RAG Isn't Dead: Navigating Retrieval vs. Agentic Search — hugobowne · 2026-08-27
- AI audit not infallible: Refine missed a known lemma error in paper — littmath · 2026-08-27
- AI audit of 19 papers: 97.7% of comments identified real issues — littmath · 2026-08-27
- Mathematician's AI-generated errata are "slop" but mostly correct — littmath · 2026-08-27
- Mathematician Litt: Paper Errors Mostly From Badly Propagated Edits, Not Deep Flaws — littmath · 2026-08-27