Reducing the Transformer Architecture to a Minimum [pdf] (arxiv.org)

2 points by DoctorOetker 1y ago ↗ HN

0 comments

[ 3.4 ms ] story [ 6.4 ms ] thread

No comments yet.

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

Source · Live DB stats