byh711
/

Qwen2.5-3B-MATH-GRPO-KOR

Reinforcement Learning

Model card Files Files and versions Community

Qwen2.5-3B-MATH-GRPO-KOR / adapter_config.json

Commit History

Initial upload of Korean Math GRPO model (Trained with Unsloth)

6af82bb
verified

byh711 commited on 4 days ago