Direct Preference Optimization: Your Language Model Is a Reward Model (arxiv.org)

2 points by ntonozzi 3y ago ↗ HN

0 comments

[ 2.3 ms ] story [ 23.0 ms ] thread

No comments yet.

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

Source · Live DB stats