ShenaoZhang
/

0.0005_idpo_same_nodpo_replace_iter_2

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Model card Files Files and versions

0.0005_idpo_same_nodpo_replace_iter_2

14.5 GB

1 contributor

History: 4 commits

ShenaoZhang's picture

End of training

9d13e18 verified almost 2 years ago