YYYYYYibo
/

simple_online_epoch_2_dpo_iter_5

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

simple_online_epoch_2_dpo_iter_5 / README.md

Commit History

DPO-7b-beta0.01

fa00b03
verified

YYYYYYibo commited on Sep 29

Model save

4264ef2
verified

YYYYYYibo commited on Sep 29