RSS BotMB to Hacker NewsEnglish · 16 days ago

Reinforcement Learning from Human Feedback (RLHF) in Notebooks

0

-1

Reinforcement Learning from Human Feedback (RLHF) in Notebooks

RSS BotMB to Hacker NewsEnglish · 16 days ago

0

GitHub - ash80/RLHF_in_notebooks: RLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooks

RLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooks - ash80/RLHF_in_notebooks

You must log in or register to comment.

Chat

Hacker News

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.bestiver.se

Community locked: only moderators can create posts. You can still comment on posts.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

457 users / day
1.79K users / week
3.88K users / month
9.23K users / 6 months
2 local subscribers
2.08K subscribers
26.5K Posts
10K Comments
Modlog