CoLT5: Faster Long-Range Transformers with Conditional Computation (arxiv.org)

4 points by 1xdevloper 3y ago ↗ HN

0 comments

[ 3.2 ms ] story [ 14.8 ms ] thread

No comments yet.

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

Source · Live DB stats