Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Compress any LLM 3x in one click,near-lossless,in under 50 MB RAM.
Any claims about throwing away 2/3rds of the model and maintaining “near lossless” quality are simply false.
There are no comments on this comment yet.
Any claims about throwing away 2/3rds of the model and maintaining “near lossless” quality are simply false.