NOVER1 - a thinkwee Collection

thinkwee 's Collections

NOVER1

NOVER1

updated 4 days ago

NOVER-series models for general reasoning

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning

Paper • 2505.16022 • Published May 21 • 3
thinkwee/NOVER1-Qwen2.5-7B

Question Answering • 8B • Updated 5 days ago • 30 • 2
thinkwee/NOVER1-Qwen3-4B

Question Answering • 4B • Updated 5 days ago • 55 • 2