Re:Fine-tune Google's Gemma 3
by moffkalast on Wednesday March 19, 2025 @06:09PM
(#43417792)
Well, why not both? If you've already got a tuned model why not use RAG on that to get even better results? It already knows the big picture, it just needs the details so it doesn't have to hallucinate them.
[ Parent
| on HN ]
Re:Fine-tune Google's Gemma 3
by danielhanchen on Wednesday March 19, 2025 @07:41PM
(#43418428)
Yes RAG combined is pretty cool! Fyi I'm planning to add optimized RAG directly into unsloth as well!