Aligning a LLM with Human Preferences - DataDreamer - discu.eu

Hacker News

RLHF a LLM in <50 lines of Python https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/aligning.html 66 comments 11/2/2024

Linked pages

[2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Model https://arxiv.org/abs/2305.18290 8 comments
https://arxiv.org/abs/2203.02155 0 comments

Would you like to stay up to date with Python? Checkout Python Weekly.

Related searches:

Search whole site: site:datadreamer.dev

Search title: Aligning a LLM with Human Preferences - DataDreamer

See how to search.

Submit link to: