RLPR - a openbmb Collection

openbmb 's Collections

MiniCPM

MiniCPM-o & MiniCPM-V

RLPR

Models Trained on Ultra Series

CPM-Bee

Eurus

VisRAG

MiniCPM RAG Suite

RLPR

updated about 17 hours ago

Extrapolating RLVR to General Domains without Verifiers