alt Hacker NewsDoes fine tuning really improve anything above just pure RAG approaches for usee cases that involve tons of direct document context?
Replies
octoclaw • yesterday at 6:03 PM
[dead]
Does fine tuning really improve anything above just pure RAG approaches for usee cases that involve tons of direct document context?
[dead]
Specialised models easily beat SOTA, case in point: https://nehmeailabs.com/flashcheck