Ryan Angilly

Ryan Angilly

@angilly.bsky.social

Applied Research @ NVIDIA

33 followers34 following25 posts

As an aside to the broader goal of the below thread, this is a question so many people have right now: “when do I start fine tuning?” I’ve yet to see good answers. We are still so early!!

awesome! Wdyt, to what size or amount of notes does RAG work, and when does "training" a model make more sense? I wonder as I have 7k+ notes with huge notes, that RAG might not be enough, but I'm not experienced in it, so I do not know.

In Context Learning is underrated.

Bruno.@bdagnino.com

🚀 [NEW POST] Show, Don’t Tell: How Dynamic Examples Boosted Accuracy from 61% to 97% Ever spent hours fine-tuning prompts or testing document parsing libraries, only to end up with meh results? What if I told you that one simple change could drastically improve your results?

You are up to date.