The Practitioner's Guide to the Maximal Update Parameterization (blog.eleuther.ai)

1 points by tipsytoad 1y ago ↗ HN

0 comments

[ 3.1 ms ] story [ 12.4 ms ] thread

No comments yet.

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

Source · Live DB stats