wrt
/

wrt_deepseek_0125

Model card Files Files and versions Metrics Training metrics Community

wrt_deepseek_0125 / deepseek-r1-7b_400_0.5_dpo_4200_rank8_epoch5_random20

1 contributor

History: 1 commit

wrt's picture

wrt

0127

5bb8d2b about 2 months ago