QLoRA 4-bit finetuning of LLMs

Posted by kashifr on Wednesday May 24, 2023 @12:59PM
from the github.com dept.

( 1 comment | on HN )

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 ]