vangard703/gpt4o-dpo-10k-gpt4o-dpo-5k-rebuttal_smooth_double_sys_temp_1e25_to_e5_gpto_small_iter_3 Updated 2 days ago • 18
vangard703/gpt4o-dpo-10k-gpt4o-dpo-5k-rebuttal_smooth_double_sys_temp_1e25_to_e5_gpto_small_iter_3 Updated 2 days ago • 18
vangard703/gpt4o-dpo-10k-double_sys_no_distribution_relabeling_temp_1e25_to_e5_gpto_small_iter_2_inverse Updated 2 days ago • 20
vangard703/gpt4o-dpo-10k-double_sys_no_distribution_relabeling_temp_1e25_to_e5_gpto_small_iter_2_inverse Updated 2 days ago • 20