.
-
yunjae-won/qwen1.7b_clip1e-6_base_step150
Text Generation • 2B • Updated • 44 -
yunjae-won/qwen1.7b_clip1e-6_base_step125
Text Generation • 2B • Updated • 33 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step150
Text Generation • 4B • Updated • 28 -
yunjae-won/qwen4b_noclip_default_KLeff_smooth_gamma1e-6_ReWeight_staticKL_reg0.5_step125
Text Generation • 4B • Updated • 33