-
yunjae-won/mpq3_qwen4bi_sft
Text Generation • 4B • Updated • 273 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step256
Text Generation • 4B • Updated • 252 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step512
Text Generation • 4B • Updated • 243 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step768
Text Generation • 4B • Updated • 257
Yunjae Won
yunjae-won
AI & ML interests
None yet
Recent Activity
updated a model about 13 hours ago
yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001 published a model about 13 hours ago
yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001 published a model about 13 hours ago
yunjae-won/ubq30i_qwen4b_dpo_topk20_j0Organizations
-
yunjae-won/mpq3_qwen4bi_sft
Text Generation • 4B • Updated • 273 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step256
Text Generation • 4B • Updated • 252 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step512
Text Generation • 4B • Updated • 243 -
yunjae-won/mpq3_qwen4bi_sft_dpo_beta1e-1_step768
Text Generation • 4B • Updated • 257
models 216
yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001
Text Generation • 0.5B • Updated
yunjae-won/ubq30i_qwen4b_dpo_topk20_j0
Text Generation • 0.5B • Updated
yunjae-won/ubq30i_qwen4b_sft_both
Text Generation • 4B • Updated • 120
yunjae-won/ubq30i_qwen4b_sft_yw
Text Generation • 4B • Updated • 71
yunjae-won/ubq30i_qwen4b_sft_yl
Text Generation • 4B • Updated • 56
yunjae-won/ub_qwen4Bi_onlineDPO-w1e-2
Updated
yunjae-won/ub_qwen0.5Bi_onlineDPO-w1e-2
Updated
yunjae-won/ub_qwen0.5Bi_onlineDPO-w1e-1
Updated
yunjae-won/ub_qwen0.5Bi_onlineDPO-test
Updated
yunjae-won/ubq30i_qwen4b_sft-Online-DPO-test
Updated
datasets 322
yunjae-won/dpo-misalignment-qwen4b-experiment-artifacts
Viewer • Updated • 12
yunjae-won/trl-ultrafeedback-qwen3-30bi-vs-4bi
Viewer • Updated • 60.9k
yunjae-won/mpr-code-qwen3-30b
Viewer • Updated • 66.2k • 15
yunjae-won/mpr-math-qwen3-1.7b
Viewer • Updated • 74.2k • 21
yunjae-won/mpr-math-qwen3-30b
Viewer • Updated • 74.2k • 12
yunjae-won/mpr-code-qwen3-4b
Viewer • Updated • 66.2k • 19
yunjae-won/mpr-math-qwen3-4b
Viewer • Updated • 74.2k • 13
yunjae-won/ub-qwen3-1.7b
Viewer • Updated • 60.9k • 14
yunjae-won/mp-qwen3-1.7b
Viewer • Updated • 100k • 31
yunjae-won/evol-qwen3-1.7b
Viewer • Updated • 78.3k • 19