teamcore/DPO_L8B_RMAB_TG_beta0.5sigmoid
Viewer • Updated • 2k • 5
AI & ML interests
None defined yet.
teamcore/DPO_L8B_RMAB_TG_beta0.5dpo_pro
Viewer • Updated • 2k • 3
teamcore/DPO_Pm3B_U0_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelEurus_RM_7bbt_noise_adv0.5
Viewer • Updated • 1k • 3
teamcore/DPO_Pm3B_U0_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelEurus_RM_7bbt_noise_adv0.25
Viewer • Updated • 1k • 2
teamcore/SFT_L8B_U0_Eurus_RM_7b
Viewer • Updated • 1k • 2
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_dro_dynamic_smooth_label_trajg
Viewer • Updated • 60 • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1dr_dpo_trajg
Viewer • Updated • 60 • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_trajg
Viewer • Updated • 60 • 2
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_traj
Viewer • Updated • 60 • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_dro_dynamic_smooth_label_traj
Viewer • Updated • 60 • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1dr_dpo_traj
Viewer • Updated • 60 • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1dr_dpobt_noise_flip0.1_traj
Viewer • Updated • 3 • 2
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoidbt_noise_flip0.3
Viewer • Updated • 1k • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_dro_dynamic_smooth_label
Viewer • Updated • 1k • 6
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoidbt_noise_adv0.25
Viewer • Updated • 1k • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelbt_noise_flip0.1
Viewer • Updated • 1k • 4
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid
Viewer • Updated • 1k • 2
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoidbt_noise_flip0.1
Viewer • Updated • 1k • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoidbt_noise_adv0.5
Viewer • Updated • 1k • 2
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelbt_noise_flip0.3
Viewer • Updated • 1k • 3
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelbt_noise_adv0.25
Viewer • Updated • 1k • 2
teamcore/DPO_L8B_RMAB_TG_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelbt_noise_adv0.5
Viewer • Updated • 1k • 2
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelEurus_RM_7bbt_noise_flip0.3g
Viewer • Updated • 1k • 2
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoidEurus_RM_7bbt_noise_flip0.3g
Viewer • Updated • 1k • 3
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoidEurus_RM_7bbt_noise_adv0.5g
Viewer • Updated • 1k • 2
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelEurus_RM_7bbt_noise_adv0.5g
Viewer • Updated • 1k • 2
teamcore/DPO_Q0.5B_U0_beta0.1dr_dpoEurus_RM_7bbt_noise_flip0.3
Viewer • Updated • 1k • 5
teamcore/DPO_Q0.5B_U0_beta0.1dr_dpoEurus_RM_7bbt_noise_flip0.1
Viewer • Updated • 1k • 4
teamcore/DPO_Q0.5B_U0_beta0.1dr_dpoEurus_RM_7bbt_noise_flip0.5
Viewer • Updated • 1k • 3
teamcore/DPO_Q0.5B_U0_beta0.1rdpoEurus_RM_7b
Viewer • Updated • 1k • 3