Re:Fine-tuned small LLMs can beat large ones with programmat...
by GabrielBianconi on Monday August 04, 2025 @03:57PM
(#44790698)
With supervised fine-tuning (SFT), you'll often see good results with 100-1000+ datapoints (they can be variations of the same prompt template). If you have more limited data, reinforcement fine-tuning (RFT) can work well in the 10-100 range.
Good luck!