PKU-Alignment

university

https://github.com/PKU-Alignment

AI & ML interests

Reinforcement Learning, Large Language Models, Value Alignment

PKU-Alignment 's datasets 40

PKU-Alignment/SafeSora

Viewer • Updated Jun 20, 2024 • 51.7k • 286 • 7

PKU-Alignment/PKU-SafeRLHF-prompt

Viewer • Updated Jun 14, 2024 • 44.6k • 312 • 5

PKU-Alignment/PKU-SafeRLHF-QA

Viewer • Updated Jun 14, 2024 • 265k • 528 • 8

PKU-Alignment/PKU-SafeRLHF-single-dimension

Viewer • Updated Jun 14, 2024 • 81.1k • 293 • 3

PKU-Alignment/processed-hh-rlhf

Viewer • Updated Nov 24, 2023 • 168k • 161 • 11

PKU-Alignment/PKU-SafeRLHF-30K

Viewer • Updated Nov 20, 2023 • 29.9k • 2.02k • 13

PKU-Alignment/BeaverTails

Viewer • Updated Oct 17, 2023 • 364k • 22.1k • 103

PKU-Alignment/BeaverTails-single-dimension-preference

Viewer • Updated Aug 18, 2023 • 29.9k • 80

PKU-Alignment/PKU-SafeRLHF-10K

Viewer • Updated Jul 20, 2023 • 10k • 1.3k • 62

PKU-Alignment/BeaverTails-Evaluation

Viewer • Updated Jul 20, 2023 • 700 • 1.02k • 14