Switch Transformers: Scaling to Trillion Parameter Models with Simple Sparsity (arxiv.org)

2 points by jbesomi 5y ago ↗ HN

0 comments

[ 3.5 ms ] story [ 12.6 ms ] thread

No comments yet.

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

Source · Live DB stats