Ururimi AI

QLoRA na 4-Bit Byiza-Guhuza

QLoRA nubuhanga butuma uhuza neza urugero rwururimi runini kumuguzi umwe GPU ubika moderi yahagaritswe mubice 4 gusa kuburemere.

2 min somaIbiherutse kuvugururwa

Incamake

It made customizing 65B-parameter models possible on hardware that previously could only handle models a fraction of that size.

Kwibira cyane

Mubisanzwe, gutunganya neza moderi nini bisobanura gupakira uburemere bwose muri 16-bit neza no kuvugurura byose, bisaba kwibuka cyane. QLoRA ikomatanya ibitekerezo bibiri. Ubwa mbere, ihagarika icyitegererezo cyateganijwe ikagereranya kugeza kuri 4 bits, igabanya kwibuka hafi inshuro enye. Icya kabiri, ikoresha LoRA: aho kuvugurura matrike nini yuburemere, itera inshinge ntoya yo gutozwa yo mu rwego rwo hasi ya adaptor matrices iruhande rwabo, bityo miriyoni nkeya gusa zikaba zivugururwa. 4-bit shingiro igumaho mugihe gradients zinyura gusa muri adaptate nto. Yamenyekanye mu 2023 na Dettmers na bagenzi be, QLoRA yerekanye ko guhuza neza moderi ya 65B kuri imwe ya 48GB GPU ishobora guhuza ubuziranenge bwuzuye 16-bitunganijwe neza.

Ubushishozi

QLoRA yerekanye amayeri atatu. NF4. Umubare wikubye kabiri ugabanya umubare uhoraho ubwabo, ukabika ububiko bwinyongera. Impapuro zogukoresha zikoresha ububiko bwa GPU-CPU kugirango zinjize imitoma mugihe kirekire, ikingira impanuka yibuka. Mugihe cyimbere ninyuma yinyuma, uburemere bwa 4 bit bitandukanijwe kugeza kuri 16-bit-gusa-mugihe cya matrix kugwira, hanyuma bikajugunywa.

Ingaruka z'Ingamba

Umuvuduko n'igipimo

Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika.

Kugera no kugera

Yagura uburyo bwindimi nuburyo bwo gutumanaho.

Ibyemezo bisobanutse

Amakipe arashobora kumara umwanya munini murubanza mugihe automatike ikora gusubiramo.

Kazoza ka QLoRA na 4-Bit Nziza-Guhuza

4-bit-neza-guhuza byahindutse imyitozo isanzwe, kandi ubushakashatsi ubu busunika kugera no kuri verisiyo yo hasi, harimo 2-bit na 1-bit (ternary). Gahunda nshya yo kubara nka AWQ, GPTQ, na HQQ inonosora neza, mugihe tekinike nka QA-LoRA igamije kugumya kwerekana urugero na nyuma yo guhuza adapt. Mugihe uburemere buremereye bugenda bwiyongera, tegereza ibikoresho bituma abashimisha bahuza neza 70B-wongeyeho moderi imwe kumikino imwe ya GPU kugirango ibe gahunda, demokarasi yihariye.

Gushyira mu bikorwa Isi

Gutangira neza-gutunganya neza moderi ya 70B Llama kuri 48GB GPU imwe kugirango yubake umufasha-wunganira abakiriya mumajwi yayo bwite adakodesha cluster ya seriveri.

Umushakashatsi ufite umuguzi umwe RTX 4090 ahuza icyitegererezo gifunguye niche yubuvuzi-busubiza dataset ijoro ryose.

Iterambere rirema udukingirizo duto duto, twahinduranya LoRA adapteri kubikorwa bitandukanye, byose bigabana moderi imwe ya 4-bit fatizo yuzuye mububiko.

Hobbyist ahindura neza icyitegererezo kumurongo wibiganiro byabo kugirango bigane uburyo bwo kwandika ukoresheje ibyuma bya Colab-yubusa.

Ingaruka & Kurinda

Ibintu bifatika bishobora kwinjiza bucece raporo, gushyigikira imigendekere, cyangwa ibisubizo byubushakashatsi.

Kwihuta byihuse birashobora gukora ibisubizo bidahuye mubisabwa bisa.

Ibyanditswe byumvikana birashobora kugaragara niba kugenzura kugenzura ari ntege.

Igishushanyo mbonera

1

Sobanura imiterere isohoka, amajwi, hamwe nubuziranenge mbere yo gutangira.

2

Ibisubizo byibanze hamwe nisoko yizewe igihe cyose ukuri kwingirakamaro.

3

Komeza kugenzura abantu kugenzura ibisubizo byinshi.

4

Kurikirana uburyo bwo kunanirwa no kongera imyitozo cyangwa akazi gahoraho.

Komeza Ubushakashatsi

Free newsletter

Get the daily AI briefing

Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.

One email each weekday. Unsubscribe in one click. We never sell or share your address.

Test yourself

Take the QLoRA and 4-Bit Fine-Tuning quiz

Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.

Tangira ikibazo

Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation

Ubuyobozi bukurikira

Kwangwa Gutoranya Cyiza-Guhuza

Ibibazo bikunze kubazwa

What is QLoRA and 4-Bit Fine-Tuning?

QLoRA nubuhanga butuma uhuza neza urugero rwururimi runini kumuguzi umwe GPU ubika moderi yahagaritswe mubice 4 gusa kuburemere. Cyakoze gukora moderi ya 65B-parameter ishoboka kubikoresho byabanje gukora gusa moderi igice cyubunini.

Niki gitekerezo cyibanze cyo kubika kwibuka inyuma ya '4-bit' igice cya QLoRA?

QLoRA ibika uburemere bwakonje bwateganijwe kuri bits 4 kuri buri gaciro, kugabanya kwibuka inshuro enye ugereranije na 16-bit.

Mugihe QLoRA itunganya neza, ni ibihe bipimo mubyukuri bigenda bivugururwa na gradient descente?

Icyitegererezo fatizo cyahagaritswe; gusa inshinge zo murwego rwo hasi adapter matrices yakira ivugurura rya gradient, nigice gito cyibipimo.

NF4 ni iki mu rwego rwa QLoRA?

NF4.

Ni ikihe kibazo 'paje optimizers' muri aderesi ya QLoRA?

Impapuro zogukoresha zikoresha GPU-CPU yibuka ihuriweho kugirango ikuremo imitsi yibuka, irinde impanuka yibuka mugihe cyo guhugura kubyinjira birebire.

Ni ryari ibiro 4-biti bihindurwa bisobanutse neza mugihe cy'amahugurwa?

Ibipimo 4-bito byujujwe kugeza kuri 16-biti neza kuguruka kuri buri matrice iragwira, hanyuma kopi yo hejuru-yuzuye ikajugunywa kugirango ibike kwibuka.