- llama3_sft_dpo_v15_8_new_rw_URM
- llama3_sft_mappo_sft_v15
- llama3_sft_mappo_v15_500_new_rw
- llama3_sft_mappo_v15_new_rw
- llama_sft_dpo_new_rw
- llama_sft_dpo_sft
- llama_sft_mappo_v15_350_new_rw
- llama_sft_mappo_v15_50_new_rw_URM
- mistral_dpo
- mistral_rapo
- qwen2.5_3B_rapo
- qwen2.5_7B_IPO_beta_0_1
- qwen2.5_7B_cpo_beta_0_001_alpha_0_01
- qwen2.5_7B_cpo_beta_0_001_alpha_0_05
- qwen2.5_7B_cpo_beta_0_001_alpha_0_1
- qwen2.5_7B_cpo_beta_0_001_alpha_0_1_lr_5e_8_iter3
- qwen2.5_7B_cpo_beta_0_001_alpha_0_2
- qwen2.5_7B_cpo_beta_0_001_alpha_0_2_lr_5e_8_iter3
- qwen2.5_7B_cpo_beta_0_01_alpha_0_01
- qwen2.5_7B_cpo_beta_0_01_alpha_0_05
- qwen2.5_7B_cpo_beta_0_01_alpha_0_1
- qwen2.5_7B_cpo_beta_0_01_alpha_0_2
- qwen2.5_7B_cpo_beta_0_01_alpha_0_2_lr_5e_8_iter3
- qwen2.5_7B_cpo_beta_0_01_alpha_0_4
- qwen2.5_7B_cpo_beta_0_01_alpha_0_4_lr_5e_8_iter3
- qwen2.5_7B_cpo_beta_0_01_alpha_1
- qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_01
- qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_05
- qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1
- qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1_lr_5e_8_iter3
- qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2
- qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2_lr_5e_8_iter3
- qwen2.5_7B_cpo_mappo_beta_0_01_alpha_0_01
- qwen2.5_7B_cpo_mappo_beta_0_01_alpha_0_1
- qwen2.5_7B_cpo_mappo_beta_0_01_alpha_0_2
- qwen2.5_7B_cpo_mappo_beta_0_01_alpha_0_2_lr_5e_8_iter3
- qwen2.5_7B_cpo_mappo_beta_0_01_alpha_0_4
- qwen2.5_7B_cpo_mappo_beta_0_01_alpha_0_4_lr_5e_8_iter3
- qwen2.5_7B_cpo_mappo_beta_0_01_alpha_1
- qwen2.5_7B_dpo_new_rw
- qwen2.5_7B_dpo_sft
- qwen2.5_7B_dpo_v15_8_new_rw_URM
- qwen2.5_7B_ipo_beta_0_01_lr_1e_7
- qwen2.5_7B_ipo_beta_0_01_lr_5e_8_iter3
- qwen2.5_7B_ipo_beta_0_1_lr_1e_7_iter3
- qwen2.5_7B_ipo_beta_0_1_lr_5e_8_iter3
- qwen2.5_7B_ipo_beta_1
- qwen2.5_7B_ipo_mappo_beta_0_01_lr_1e_7_iter3
- qwen2.5_7B_ipo_mappo_beta_0_01_lr_5e_8_iter3
- qwen2.5_7B_ipo_mappo_beta_0_1