DolbyUUU / Logic-RL-Lite
View external linksLinks

Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".
50Apr 1, 2025Updated 10 months ago

Alternatives and similar repositories for Logic-RL-Lite

Users that are interested in Logic-RL-Lite are comparing it to the libraries listed below

Sorting:

Are these results useful?