yunjae-won/OPD_4b_noclip_default_staticKL_reg1_step50
Text Generation • 4B • Updated • 27
Yunjae Won
yunjae-won
AI & ML interests
None yet
Recent Activity
published a bucket 6 days ago
yunjae-won/Openthoughts_math_30k_opsd_clone published a model 6 days ago
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step25 published a model 6 days ago
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step100Organizations
yunjae-won/OPD_4b_noclip_default_KLinefficiency_direct_step50
Text Generation • 4B • Updated • 23
yunjae-won/OPD_4b_noclip_default_staticKL_reg1_step25
Text Generation • 4B • Updated • 28
yunjae-won/OPD_4b_noclip_default_KLinefficiency_direct_step25
Text Generation • 4B • Updated • 32
yunjae-won/qwen3_4b_OPD_warmup_step50
Text Generation • 4B • Updated • 649
yunjae-won/qwen1.7b_clip1e-6_base_step50
Updated
yunjae-won/qwen1.7b_clip1e-6_base_step125
Text Generation • 2B • Updated • 3
yunjae-won/qwen1.7b_clip1e-6_base_step150
Text Generation • 2B • Updated • 4
yunjae-won/qwen1.7b_clip1e-6_base_step75
Updated
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step50
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step100
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step75
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step25
Text Generation • 2B • Updated • 3 • 1
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step25
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step50
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step75
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step200
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step175
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step100
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step125
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step150
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step50
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step75
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step200
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step25
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step100
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step125
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step175
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-staticKL-reg0.5_step150
Text Generation • 2B • Updated • 2
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg1.0_step25
Text Generation • 2B • Updated • 2