dataset
DeepEnlighten
DolbyUUU
or hover any field below to flag it
Overview
Name
DeepEnlighten
Source
DolbyUUU
Episodes
0
Robot count
0
Format
other
Description
Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.
Robots used
null
Links
HuggingFace dataset
null