DolbyUUU / DeepEnlighten
View external linksLinks

Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.
39Mar 16, 2025Updated 10 months ago

Alternatives and similar repositories for DeepEnlighten

Users that are interested in DeepEnlighten are comparing it to the libraries listed below

Sorting:

Are these results useful?