AlphaPruning: Using Heavy-Tailed Self Regularization for Improved LLM Pruning (arxiv.org)

1 points by selimthegrim 1y ago ↗ HN

0 comments

[ 3.4 ms ] story [ 15.4 ms ] thread

No comments yet.

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

Source · Live DB stats