GeorgiaTech
/

0.0005_zephyr_withdpo_5551_4iters_bs256_newtrl_iter_3

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Model card Files Files and versions

0.0005_zephyr_withdpo_5551_4iters_bs256_newtrl_iter_3

14.5 GB

1 contributor

History: 3 commits

ZhangShenao's picture

End of training

94b1bed verified over 1 year ago