QLoRA 4-bit finetuning of LLMs | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		QLoRA 4-bit finetuning of LLMs (github.com/artidoro)
		7 points by kashifr on May 24, 2023 \| hide \| past \| favorite \| 1 comment

kashifr on May 24, 2023 [–]

An efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact