DUAL-GPO
/

zephyr-7b-dpo-0k-15k-i1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-0k-15k-i1 / tokenizer.model

Commit History

Training in progress, step 20

901fc5f
verified

BraylonDash commited on Sep 18