all domains
10·1 notion

Fine-tuning

LoRA, QLoRA, RLHF, DPO, synthetic data. Specializing a model for a use case.

Apr 13,

LoRA Adapters

Lightweight fine-tuning where you train small "delta weights" (low-rank) instead of the full model. 100-1000x fewer parameters, GPU memory divided, and adapters can be loaded **at runtime** to specialize a generalist model for a use case.