Metodebevisregistrering
LoRA and PEFT
LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched.
Kilderegistrering
Citater kopieret ordret fra metodens kilderegistrering. Ingen påstandsniveauverifikation er udledt heraf.
Low-Rank Adaptation and Parameter-Efficient Fine-Tuning
Taksonomisk metoderegistrering · ml-model / deep-learning
- Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR. · URL
- Lester, B. et al. (2021). The Power of Scale for Parameter-Efficient Prompt Tuning. EMNLP. · DOI 10.18653/v1/2021.emnlp-main.243
Kuraterede påstande
Påstande gemt i bevis-loggen, hver med sin egen vurdering.
Ingen kuraterede påstande endnu
Denne visning opfinder ikke en påstandsvurdering, når loggen ingen har.
Relaterede metoder
Genereret fra metodegrafen og vist som maskinelt foreslåede relationer — ingen bevispåstand er udledt.