fusion-llm-demo / train /train_grpo.py

Commit History

fix: audit v2 P0/P1 fixes (D1/D2/D3/D7/D9/D11/D14)
5e7eab2

zhan1206 commited on

fix: distillation script uses FusionModel + add GRPO training script
4bf76ff

zhan1206 commited on