Holarissun
/

REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-05

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-05

Commit History

harmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-05

1bca99e
verified

Holarissun commited on May 24

initial commit

e498c5f
verified

Holarissun commited on May 24