News for hackers. Stuff that matters.
Re:QuIP#: 2-bit Quantization for LLMs by gumby on Friday December 08, 2023 @10:17PM (#38578187)
There was a paper from the Allen institute from around 2017 successfully using 1 bit quantization but I can’t find it right now. We started using it where I was working at the time but I’m no longer there so I don’t know how it all turned out.

There are no comments on this comment yet.