RLPR: Extrapolating RLVR to General Domains without Verifiers
Paper • 2506.18254 • Published • 35
RLPR
Extrapolating RLVR to General Domains without Verifiers
-
-
openbmb/RLPR-Train-Dataset
Viewer • Updated • 77.7k • 258 • 29 -
openbmb/RLPR-Qwen2.5-7B-Base
Text Generation • 8B • Updated • 71 • 9 -
openbmb/RLPR-Gemma2-2B-it
Text Generation • 3B • Updated • 76 • 4 -
openbmb/RLPR-Llama3.1-8B-Inst
Text Generation • 8B • Updated • 57 • 4 -
openbmb/RLPR-Evaluation
Viewer • Updated • 638 • 414 • 3