DoWG parameter-free adaptive optimizer
Project description
This is an implementation of the DoWG optimization algorithm as laid out by Khaled et al.. I am unsure if the implementation is correct, and I took the liberty of creating a quantized implementation under DoWG8bit as the ordinary version absolutely gobbles up Vram.
Pull requests are welcome.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
dowg-0.2.2.tar.gz
(3.7 kB
view hashes)
Built Distribution
dowg-0.2.2-py3-none-any.whl
(4.6 kB
view hashes)
