News for hackers. Stuff that matters.

A comment on QLoRA: Efficient Finetuning of Quantized LLMs. Parent comment

Re:QLoRA: Efficient Finetuning of Quantized LLMs by sanxiyn on Wednesday May 24, 2023 @09:32PM (#36066146)
For quality, GPTQ-for-LLaMa repository README is already updated for comparison with this work. See under "GPTQ vs bitsandbytes".
[ Parent | on HN ]
Re:QLoRA: Efficient Finetuning of Quantized LLMs by sp332 on Wednesday May 24, 2023 @10:48PM (#36066546)
https://github.com/qwopqwop200/GPTQ-for-LLaMa
[ Parent | on HN ]