News for hackers. Stuff that matters.
Re:QLoRA: Efficient Finetuning of Quantized LLMs by nl on Wednesday May 24, 2023 @07:53PM (#36065466)
Tim Dettmers is such a star. He's probably done more to make low-resource LLMs usable than anyone else.

First bitsandbytes[1] and now this.

[1] https://github.com/TimDettmers/bitsandbytes

Re:QLoRA: Efficient Finetuning of Quantized LLMs by m3affan on Thursday May 25, 2023 @07:27AM (#36069350)
Thanks for pointing this out. Such projects deserve visibility.