.
Yunjae Won
yunjae-won
AI & ML interests
None yet
Recent Activity
published a model about 23 hours ago
yunjae-won/qwen1.7b_clip1e-6_base_step50 published a model about 24 hours ago
yunjae-won/qwen1.7b_clip1e-6_base_step75 updated a collection about 24 hours ago
On-Policy Distillation AnalysisOrganizations
dpo-info-loss
-
yunjae-won/mpq3_qwen4bi_sft
Text Generation • 4B • Updated • 9 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step256
Text Generation • 4B • Updated • 9 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step512
Text Generation • 4B • Updated • 9 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step768
Text Generation • 4B • Updated • 9
On-Policy Distillation Analysis
.
dpo-info-loss
-
yunjae-won/mpq3_qwen4bi_sft
Text Generation • 4B • Updated • 9 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step256
Text Generation • 4B • Updated • 9 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step512
Text Generation • 4B • Updated • 9 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step768
Text Generation • 4B • Updated • 9
models 309
yunjae-won/qwen1.7b_clip1e-6_base_step50
Updated
yunjae-won/qwen1.7b_clip1e-6_base_step125
Text Generation • 2B • Updated • 13
yunjae-won/qwen1.7b_clip1e-6_base_step150
Text Generation • 2B • Updated • 12
yunjae-won/qwen1.7b_clip1e-6_base_step75
Updated
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step50
Text Generation • 2B • Updated • 18
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step100
Text Generation • 2B • Updated • 24
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step75
Text Generation • 2B • Updated • 25
yunjae-won/1.7b-fwdkl-clip1e-6-lora-debug_step25
Text Generation • 2B • Updated • 21 • 1
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step25
Text Generation • 2B • Updated • 25
yunjae-won/1.7b-fwdkl-clip1e-6-lora-adaKL-reg0.5_step50
Text Generation • 2B • Updated • 27
datasets 322
yunjae-won/dpo-misalignment-qwen4b-experiment-artifacts
Viewer • Updated • 12 • 99
yunjae-won/trl-ultrafeedback-qwen3-30bi-vs-4bi
Viewer • Updated • 60.9k • 68
yunjae-won/mpr-code-qwen3-30b
Viewer • Updated • 66.2k • 91
yunjae-won/mpr-math-qwen3-1.7b
Viewer • Updated • 74.2k • 19
yunjae-won/mpr-math-qwen3-30b
Viewer • Updated • 74.2k • 110
yunjae-won/mpr-code-qwen3-4b
Viewer • Updated • 66.2k • 93
yunjae-won/mpr-math-qwen3-4b
Viewer • Updated • 74.2k • 25
yunjae-won/ub-qwen3-1.7b
Viewer • Updated • 60.9k • 26
yunjae-won/mp-qwen3-1.7b
Viewer • Updated • 100k • 23
yunjae-won/evol-qwen3-1.7b
Viewer • Updated • 78.3k • 13