On-Policy Distillation Analysis . yunjae-won/qwen1.7b_clip1e-6_base_step150 Text Generation • 2B • Updated Jun 7 • 2 yunjae-won/qwen1.7b_clip1e-6_base_step125 Text Generation • 2B • Updated Jun 7 • 2 yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step150 Text Generation • 4B • Updated 14 days ago • 33 yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step125 Text Generation • 4B • Updated 14 days ago • 36
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step150 Text Generation • 4B • Updated 14 days ago • 33
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step125 Text Generation • 4B • Updated 14 days ago • 36
dpo-info-loss yunjae-won/mpq3_qwen4bi_sft Text Generation • 4B • Updated Apr 7 • 6 yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step256 Text Generation • 4B • Updated Apr 6 • 6 yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step512 Text Generation • 4B • Updated Apr 6 • 7 yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step768 Text Generation • 4B • Updated Apr 6 • 6
On-Policy Distillation Analysis . yunjae-won/qwen1.7b_clip1e-6_base_step150 Text Generation • 2B • Updated Jun 7 • 2 yunjae-won/qwen1.7b_clip1e-6_base_step125 Text Generation • 2B • Updated Jun 7 • 2 yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step150 Text Generation • 4B • Updated 14 days ago • 33 yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step125 Text Generation • 4B • Updated 14 days ago • 36
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step150 Text Generation • 4B • Updated 14 days ago • 33
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step125 Text Generation • 4B • Updated 14 days ago • 36
dpo-info-loss yunjae-won/mpq3_qwen4bi_sft Text Generation • 4B • Updated Apr 7 • 6 yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step256 Text Generation • 4B • Updated Apr 6 • 6 yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step512 Text Generation • 4B • Updated Apr 6 • 7 yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step768 Text Generation • 4B • Updated Apr 6 • 6
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-200 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-175 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-150 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-125 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-100 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-75 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-50 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg2_checkpoint-25 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg1_checkpoint-200 Updated about 9 hours ago
yunjae-won/OPSD_1.7b_noclip_default_lr5e-6_bs64_staticKL_reg1_checkpoint-175 Updated about 9 hours ago