Training Compact Transformers from Scratch in 30 Minutes with PyTorch (medium.com)

3 points by godelski 5y ago ↗ HN

0 comments

[ 3.2 ms ] story [ 11.6 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats