JayHyeon/Qwen_0.5-VDPO_5e-7_5vpo_constant_ls0.0_seed42 Text Generation • 0.6B • Updated 11 days ago • 9
JayHyeon/Qwen_0.5-VDPO_5e-7_3.0vpo_constant_ls0.0_seed42 Text Generation • 0.6B • Updated 11 days ago • 13
JayHyeon/Qwen_0.5-VDPO_5e-7_0.3vpo_constant_ls0.0_seed42 Text Generation • 0.6B • Updated 11 days ago • 14
JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.3_seed42 Text Generation • 0.6B • Updated 12 days ago • 17
JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42 Text Generation • 0.6B • Updated 12 days ago • 13
JayHyeon/Qwen_0.5-rDPO_5e-7_1.0vpo_constant_ls0.1_seed42 Text Generation • 0.6B • Updated 12 days ago • 14
JayHyeon/Qwen_0.5-rDPO_5e-7_1.0vpo_constant_ls0.3_seed42 Text Generation • 0.6B • Updated 12 days ago • 16
JayHyeon/Qwen_0.5-VIPO_5e-7_1.0vpo_constant_ls0.0_seed42 Text Generation • 0.6B • Updated 12 days ago • 14
JayHyeon/Qwen_0.5-IPO_5e-7_1.0vpo_constant_ls0.0_seed42 Text Generation • 0.6B • Updated 12 days ago • 14
JayHyeon/Qwen_0.5-VDPO_5e-7_1.0vpo_constant_ls0.0_seed42 Text Generation • 0.6B • Updated 12 days ago • 18
JayHyeon/Qwen_0.5-DPO_5e-7_1.0vpo_constant_ls0.0_seed42 Text Generation • 0.6B • Updated 12 days ago • 14
JayHyeon/Qwen_0.5-rDPO_5e-7_0.3lsmooth-1.0vpo_constant Text Generation • 0.6B • Updated 14 days ago • 10
JayHyeon/Qwen_0.5-rDPO_5e-7_0.1lsmooth-1.0vpo_constant Text Generation • 0.6B • Updated 15 days ago • 11
JayHyeon/Qwen_0.5-rDPO_5e-7_1.0vpo_constant_0.3label_smoothing Text Generation • 0.6B • Updated 16 days ago • 15
JayHyeon/Qwen_0.5-rDPO_5e-7_1.0vpo_constant_0.1label_smoothing Text Generation • 0.6B • Updated 16 days ago • 14
JayHyeon/Qwen_0.5-VDPO_5e-7_3.0vpo_constant_0.3label_smoothing Text Generation • 0.6B • Updated 18 days ago • 15
JayHyeon/Qwen_0.5-cDPO_5e-7_0.1lsmooth-1.0vpo_constant-1ep Text Generation • 0.6B • Updated 18 days ago • 15
JayHyeon/Qwen_0.5-VDPO_5e-7_1.0vpo_constant_0.1label_smoothing Text Generation • 0.6B • Updated 18 days ago • 14
JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_0.3label_smoothing Text Generation • 0.6B • Updated 18 days ago • 16