Article
Deriving the PPO Loss from First Principles
•
37
Aleksandar Vakanski PRO
avakanski
AI & ML interests
None yet
Recent Activity
updated
a dataset 24 days ago
avakanski/dpo-QA-beavertails-1k-qwen-formatted published
a dataset 24 days ago
avakanski/dpo-QA-beavertails-1k-qwen-formatted updated
a dataset 24 days ago
avakanski/harmful-QA-beavertails-1k-qwen-formatted Organizations
upvoted an article 3 months ago