Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Paper
•
2503.16219
•
Published
•
48
Open-RS
Model weights & datasets in the paper "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t"
-
-
knoveleng/OpenRS-GRPO
Text Generation • Updated • 75 • 5 -
knoveleng/Open-RS1
Text Generation • Updated • 543 • 4 -
knoveleng/Open-RS2
Text Generation • Updated • 438 • 1 -
knoveleng/Open-RS3
Text Generation • Updated • 2.55k • 19 -
knoveleng/open-rs
Viewer • Updated • 7k • 2.31k • 9 -
knoveleng/open-s1
Viewer • Updated • 18.6k • 400 • 4 -
knoveleng/open-deepscaler
Viewer • Updated • 21k • 180 • 4