Holarissun
/

REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Commit History

harmless_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

a40b28d
verified

Holarissun commited on May 28

initial commit

094f974
verified

Holarissun commited on May 28