Holarissun
/

REPROD_dpo_harmlessharmless_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_harmlessharmless_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06 / README.md

Commit History

harmless_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

4a0cea2
verified

Holarissun commited on May 29