Showing 1–3 of 3 · #fine-tuning
PAPERSLoRA in plain English
Fine-tune a large model by training less than one percent of it. How low-rank adapters work, what QLoRA adds and when to use them.
SPSana PatelNov 03 · 6 min
PAPERSPreference tuning: RLHF and DPO side by side
Reward models and PPO versus a single elegant loss. How RLHF and DPO turn human preferences into model behaviour, and what each costs.
SPSana PatelAug 20 · 6 min
MODELSDistillation explained for builders
Train a small model to imitate a big one and keep most of the quality at a fraction of the cost. How it works, when it pays off and what to check first.
JLJonas LindJul 30 · 6 min