Has anyone tried RLHF on the GPT models when fine-tuning? Would this be useful?

2 points by jmiran15 3y ago ↗ HN

0 comments

[ 2.5 ms ] story [ 9.9 ms ] thread

No comments yet.

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

Source · Live DB stats