Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05 Updated May 24 • 2
Holarissun/REPROD_dpo_helpfulhelpful_gpt3_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05 Updated May 24 • 2 • 1
Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-06 Updated May 24 • 2
Holarissun/REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05 Updated May 24 • 3
Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-05 Updated May 24 • 2