ScholarGate
Msaidizi
Machine learningDeep Learning, Language Models, Parameter Efficient Fine-Tuning

QLoRA

QLoRA ni mbinu bora ya urekebishaji iliyoanzishwa na Dettmers et al. mwaka 2023 ambayo huwezesha urekebishaji wa miundo mikuu ya lugha kwa kutumia upimaji na urekebishaji wa kiwango cha chini. Kwa kuchanganya upimaji wa biti 4 na LoRA, QLoRA hupunguza mahitaji ya kumbukumbu kwa 75%, ikiwezesha urekebishaji wa miundo yenye vigezo bilioni 65 kwenye GPU moja.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

The neighbourhood of related methods — select a node to explore.

Vyanzo

  1. Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Efficient Finetuning of Quantized LLMs. ScholarGate. https://scholargate.app/sw/deep-learning/qlora

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Imerejelewa na

ScholarGateQLoRA (Efficient Finetuning of Quantized LLMs). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/qlora · Seti ya data: https://doi.org/10.5281/zenodo.20539026