News for hackers. Stuff that matters.

A comment on QLoRA 4-bit finetuning of LLMs.

Re:QLoRA 4-bit finetuning of LLMs by kashifr on Wednesday May 24, 2023 @01:01PM (#36060973)
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!
[ Parent | on HN ]

There are no comments on this comment yet.