AI & ML interests
None defined yet.
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelEurus_RM_7b
Updated
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoidEurus_RM_7b
Updated
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelEurus_RM_7bbt_prob_noise0.5
Updated
teamcore/DPO_Q0.5B_U0_beta0.1generalized_sigmoid_dro_dynamic_smooth_labelEurus_RM_7blabel_switching0.4
Updated
teamcore/DPO_Q0.5B_U0_beta0.1loss_typegeneralized_sigmoid_dro_dynamic_smooth_labelreward_modelEurus_RM_7b
Updated
teamcore/DPO_Q0.5B_U0_beta0.1loss_typegeneralized_sigmoidreward_modelEurus_RM_7b
Updated
teamcore/SFT_Q0.5B_U0_reward_modelEurus_RM_7bnoise_typebt_prob_noise0.1
Updated
teamcore/SFT_Q0.5B_U0_reward_modelEurus_RM_7bnoise_typelabel_switching0.4
Updated
teamcore/SFT_Q0.5B_U0_reward_modelEurus_RM_7bnoise_typelabel_switching0.1
Updated
teamcore/SFT_Q0.5B_U0_reward_modelEurus_RM_7b
Updated
teamcore/SFT_Q0.5B_U0_reward_modelEurus_RM_7bnoise_typebt_prob_noise0.5
Updated
teamcore/DPO_Q0.5B_U0_beta0.1loss_typegeneralized_sigmoid_dro_dynamic_smooth_label
Updated
teamcore/DPO_Q0.5B_U0_beta0.1loss_typegeneralized_sigmoid_smooth_label
Updated
teamcore/DPO_Q0.5B_U0_beta0.1loss_typegeneralized_sigmoid_dynamic_smooth_label
Updated
teamcore/DPO_Q0.5B_U0_beta0.1loss_typegeneralized_sigmoid
Updated
teamcore/DPO_Q0.5B_U0_beta0.1loss_typerev_generalized_sigmoid_dro_dynamic_smooth_label
Updated
teamcore/DPR_Q0.5B_U0_beta0.1g0.3gamma0.3loss_typegeneralized_sigmoid
Updated
teamcore/DPR_Q0.5B_U0_beta0.1g0.3gamma0.3loss_typegeneralized_sigmoid_dro_dynamic_smooth_label
Updated
teamcore/DPR_Q0.5B_U0_beta0.1g0.3gamma0.3loss_typegeneralized_sigmoid_old
Updated
teamcore/DPO_Q0.5B_U0_full_beta0.1loss_typegeneralized_sigmoid
Updated
teamcore/SFT_Q0.5B_U0_low_epochs
Updated
teamcore/DPR_Py70M_U0_beta0.1g0.3gamma0.3loss_typegeneralized_sigmoid
Updated
teamcore/DPR_Py70M_U0_beta0.1g0.3gamma0.3loss_typegeneralized_sigmoid_dro_dynamic_smooth_label
Updated
teamcore/DPR_Py70M_U0_beta0.1g0.3gamma0.3loss_typegeneralized_sigmoid_dynamic_smooth_label
Updated
teamcore/DPR_Py70M_U0_beta0.1g0.3gamma0.3loss_typegeneralized_sigmoid_smooth_label
Updated
teamcore/DPO_Py70M_U0_beta0.1loss_typegeneralized_sigmoid
Updated
teamcore/DPO_Py70M_U0_beta0.1loss_typegeneralized_sigmoid_smooth_label
Updated
teamcore/DPO_Py70M_U0_beta0.10_generalized_sigmoid_smooth_label
Updated
teamcore/DPO_Py70M_U0_beta0.10
Updated