Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-05 Updated 26 days ago
Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-05 Updated 26 days ago