AI Grimoire
03 — siblings
sft/
peft/

Fine-tuning / peft

Parameter-efficient methods

Full fine-tuning updates every weight and needs optimiser state for all of them. The methods here constrain the update to a low-rank or quantised form, which makes tuning cheap, adapters portable, and merging several of them into one model a question with an actual answer.

4 entries, 1 of them a stub.

Entries

03.02.1
Adapter Mergingstubcommon
Task arithmetic, TIES and DARE over independently trained deltas.
O(d)
03.02.2
DoRAcommon
Low-rank adaptation split into a magnitude and a direction.
O(r·d)
03.02.3
LoRAstandard
Low-rank additive update to frozen weight matrices during adaptation.
O(r·d)
03.02.4
QLoRAstandard
4-bit NF4 base weights with paged optimiser state and LoRA adapters.
O(r·d)