BayesRL/Olmo3-B3PO-7B
Text Generation • 7B • Updated • 9
3PO Models
3PO family methods trained on DapoMath-17k using Olmo3-IVON-SFT-7B and Qwen2.5Math-IVON-SFT-7B
-
-
BayesRL/Olmo3-M3PO-7B
Text Generation • 7B • Updated • 6 -
BayesRL/Olmo3-C3PO-7B
Text Generation • 7B • Updated • 10 -
BayesRL/Olmo3-M3POPlus-7B
Text Generation • 7B • Updated • 9 -
BayesRL/Olmo3-B3PO_MC-7B
Text Generation • 7B • Updated • 12 -
BayesRL/Olmo3-C3PO_MC-7B
Text Generation • 7B • Updated • 7 -
BayesRL/Qwen-B3PO-7B
Text Generation • 8B • Updated • 81 -
BayesRL/Qwen-M3PO-7B
Text Generation • 8B • Updated • 13 -
BayesRL/Qwen-C3PO-7B
Text Generation • 8B • Updated • 77 -
Parameter Exploration for RLVR via Variational Learning
Paper • 2608.09805 • Published • 5