Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06 Updated 1 day ago
Holarissun/REPROD_dpo_helpfulhelpful_gpt3_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06 Updated 5 days ago
Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr1e-05 Updated 5 days ago
Holarissun/REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06 Updated 5 days ago
Holarissun/REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05 Updated 5 days ago
Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma2b_maxsteps6000_bz8_lr5e-06 Updated 5 days ago
Holarissun/REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma2b_maxsteps10000_bz8_lr1e-05 Updated 5 days ago