feat(rl): Filter incomplete trajectories that hit max_tokens limit#160
Open
EvanZhuang wants to merge 2 commits intothinking-machines-lab:mainfrom
Open
feat(rl): Filter incomplete trajectories that hit max_tokens limit#160EvanZhuang wants to merge 2 commits intothinking-machines-lab:mainfrom
EvanZhuang wants to merge 2 commits intothinking-machines-lab:mainfrom