Vector Post-Training Quantization (VPTQ) is a novel Post-Training Quantization method that leverages Vector Quantization to high accuracy on LLMs at an extremely low bit-width (<2-bit). VPTQ can ...
This pack contains many mods, including some that might not play nice with Sodium such as Chisels & Bits, Tinkers, Create, and more. While I expect some jank, this constant memory leak is definitely ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback