yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step150 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step150 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step125 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step125 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step100 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step100 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step75 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step75 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step50 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step50 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step25 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step150 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg2_step25 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step150 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step150 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step125 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step150 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_KLinefficiency_direct_ReWeight_Warmup_adaKL_reg1_step125 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step125 Text Generation • 4B • Updated 1 day ago
yunjae-won/4b_noclip_default_ReWeight_Warmup_staticKL_reg1_step100 Text Generation • 4B • Updated 1 day ago