Unakar/Logic-RL

Reproduce R1 Zero on Logic Puzzle

1 best points · 0 comments · 1 Hacker News post · 2,452 GitHub stars · View on GitHub

Hacker News discussions

• Logic R1: Reproduce DeepSeek R1 Zero on 2K Logic Puzzle Dataset (1 points, 0 comments, by limoce, 2025-02-05)