kiante

xkianteb 's models 16

Sort:  Recently updated

xkianteb/dpo_top1_nolog_equal_weight_lr_1e-6_beta_0.5_555134_1725236314

Text Generation • 8B • Updated Sep 2, 2024 • 2

xkianteb/dpo_top1_nolog_lr_3e-7_beta_1.0_555134_1725219001

Text Generation • 8B • Updated Sep 1, 2024 • 2

xkianteb/simpo_1e-6_sigmoid

Text Generation • 8B • Updated Aug 17, 2024 • 2

xkianteb/simpo_1e-6_squared

Text Generation • 8B • Updated Aug 16, 2024 • 1

xkianteb/ipo_scale_1e-6_0.001_1723740002

Text Generation • 8B • Updated Aug 15, 2024 • 2

xkianteb/ipo_scale_1e-6_beta_0.1_1723688553

Text Generation • 8B • Updated Aug 15, 2024 • 2

xkianteb/ipo_1e-6_beta_0.1_1723688553

Text Generation • 8B • Updated Aug 15, 2024 • 2

xkianteb/ipo_scale_3e-7_1723651980

Text Generation • 8B • Updated Aug 14, 2024 • 2

xkianteb/ipo_scale_1e-6_1723651982

Text Generation • 8B • Updated Aug 14, 2024 • 2

xkianteb/dpo_1e-6_1723651057

Text Generation • 8B • Updated Aug 14, 2024 • 3

xkianteb/dpo_3e-7_1723256865

Text Generation • 8B • Updated Aug 14, 2024 • 2

xkianteb/rebel_simpo_eta_100_1723490604

Text Generation • 8B • Updated Aug 13, 2024 • 3

xkianteb/rebel_simpo_eta_1e6_1723490603

Text Generation • 8B • Updated Aug 13, 2024 • 2

xkianteb/simpo_1e-6_v2_1723258289

Text Generation • 8B • Updated Aug 12, 2024 • 2

xkianteb/dpo_simpo_3e-7_1723259355

Text Generation • 8B • Updated Aug 11, 2024 • 2

xkianteb/dpo_simpo_1e-6_v9_1723259406

Text Generation • 8B • Updated Aug 11, 2024 • 2