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 • 620 • 4 -
knoveleng/Open-RS2
Text Generation • Updated • 504 • 1 -
knoveleng/Open-RS3
Text Generation • Updated • 2.92k • 19 -
knoveleng/open-rs
Viewer • Updated • 7k • 1.32k • 10 -
knoveleng/open-s1
Viewer • Updated • 18.6k • 346 • 4 -
knoveleng/open-deepscaler
Viewer • Updated • 21k • 134 • 4