quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
LoRA — A cheap way to fine-tune a model by training a small add-on layer instead of changing all of the model's weights.
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
Why it matters
It collapsed the hardware bar for fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition → a large model from a cluster to one GPU, by backpropagating through 4-bit frozen weights into low-rank adapters. If you have ever fine-tuned anything on your own machine, this is the paper that made it possible.
