anthropics/
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
Archived by Anthropic MIT licence 169 forks Created Apr 2022 View on GitHub
- Stars
- 1,862
- <1% of anthropics's stars
- Rank
- #36,731
- of 852,045 repos, top 5%
Among 852,045 repos
1.6k–2.5k stars: 15,655 repos, including hh-rlhf
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #36,710
- Next milestone
- +5,350 stars to reach the top 1%
- Popular
- One of 66,553 repos with 1k+ stars
- Yearly average
- 405 stars a year since Apr 2022