LightMySky

Adapting a Pretrained Model: Fine-Tuning and Low-Rank Updates

Most work starts from weights someone else paid for. A full fine-tune moves every parameter and costs a whole copy to store, while a low-rank update trains a small factored correction and leaves the base weights alone.

No account needed. Progress saves in this browser.

What a learner can do afterwards

  • Compare parameter count and storage for a full fine-tune against a low-rank adapter
  • Say when adapting beats prompting for a task, and when it does not
  • Describe catastrophic forgetting and one measure that keeps it in check

1 · Read

Most work starts from weights someone else paid for. A full fine-tune moves every parameter and costs a whole copy to store. A low-rank update instead trains a small factored correction and leaves the base weights alone: the update is the product of two thin matrices, B times A.

Count the storage before you choose. A full n by n update stores n squared numbers, while the factored pair stores 2 times n times the rank. The adapter wins whenever the rank sits below half the size. A 4 by 4 layer with rank 2 stores 16 numbers, the same as full, while a 100 by 100 layer with rank 4 stores 800 against 10000, and rank 60 stores 12000, worse than full. If a matrix has rank 1, every row is a multiple of the first: with rows [2, 4] and [3, x], 3 is 1.5 times 2, so x is 1.5 times 4, which is 6.

Try it together

Pick prompting when the need is one-off or the budget is thin, since no training runs at all. Pick adapting when the task repeats often enough to repay training and prompting keeps missing. Between adapters, pick a low rank when storage and forgetting matter, and pay for fuller moves only when the task demands capacity the thin update cannot hold.

Good to know

Full moves risk catastrophic forgetting: new training washes out old skills. Keep old-task checks running as you train, freeze more and train less where you can, and stop when the old scores start to slip.

Train a thin factored correction when it suffices, count 2 n r against n squared, and watch old tasks while you adapt.

2 · Watch

Take it off screen

Print a worksheetA4 with an answer key page for grown-ups. No screen, no internet.

Where it sits

Then practise

8 questions wait behind this lesson, each with its answer explained. Every answer feeds the sky: stars light as they are learned, and dim when it is time to come back.

Spotted a problem on this page? Tell us
Adapting a Pretrained Model: Fine-Tuning and Low-Rank Updates · Computing, ages 22 to 24 · LightMySky