News for hackers. Stuff that matters.

A comment on Towards Optimal LLM Quantization.

Re:Towards Optimal LLM Quantization by dynamix on Thursday May 30, 2024 @02:03PM (#40526781)
Is there a way for me to compress a custom fine-tuned model of my own?
[ Parent | on HN ]
Re:Towards Optimal LLM Quantization by bejager on Thursday May 30, 2024 @02:10PM (#40526869)
not yet but it's something we have in mind as a future feature.
[ Parent | on HN ]