Yunjae Won

yunjae-won's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 6 days ago

yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001

Text Generation • 0.5B • Updated 6 days ago • 207

published 2 models 6 days ago

yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001

Text Generation • 0.5B • Updated 6 days ago • 207

yunjae-won/ubq30i_qwen4b_dpo_topk20_j0

Text Generation • 0.5B • Updated 6 days ago • 219

updated a dataset 6 days ago

yunjae-won/dpo-misalignment-qwen4b-experiment-artifacts

Viewer • Updated 6 days ago • 12 • 20

published a dataset 6 days ago

yunjae-won/dpo-misalignment-qwen4b-experiment-artifacts

Viewer • Updated 6 days ago • 12 • 20

updated a model 7 days ago

yunjae-won/ubq30i_qwen4b_dpo_topk20_j0

Text Generation • 0.5B • Updated 6 days ago • 219

updated a dataset 7 days ago

yunjae-won/trl-ultrafeedback-qwen3-30bi-vs-4bi

Viewer • Updated 7 days ago • 60.9k • 37

published a dataset 7 days ago

yunjae-won/trl-ultrafeedback-qwen3-30bi-vs-4bi

Viewer • Updated 7 days ago • 60.9k • 37

updated a model 7 days ago

yunjae-won/ubq30i_qwen4b_sft_both

Text Generation • 4B • Updated 7 days ago • 983

published a model 7 days ago

yunjae-won/ubq30i_qwen4b_sft_both

Text Generation • 4B • Updated 7 days ago • 983

updated a model 7 days ago

yunjae-won/ubq30i_qwen4b_sft_yw

Text Generation • 4B • Updated 7 days ago • 457

published a model 7 days ago

yunjae-won/ubq30i_qwen4b_sft_yw

Text Generation • 4B • Updated 7 days ago • 457

updated a model 7 days ago

yunjae-won/ubq30i_qwen4b_sft_yl

Text Generation • 4B • Updated 7 days ago • 450

published a model 7 days ago

yunjae-won/ubq30i_qwen4b_sft_yl

Text Generation • 4B • Updated 7 days ago • 450

published 5 models 8 days ago

yunjae-won/ub_qwen4Bi_onlineDPO-w1e-2

Updated 8 days ago

yunjae-won/ub_qwen0.5Bi_onlineDPO-w1e-2

Updated 8 days ago

yunjae-won/ub_qwen0.5Bi_onlineDPO-w1e-1

Updated 8 days ago

yunjae-won/ub_qwen0.5Bi_onlineDPO-test

Updated 8 days ago

yunjae-won/ubq30i_qwen4b_sft-Online-DPO-test

Updated 8 days ago

published a model 10 days ago

yunjae-won/Qwen2.5-0.5B-Online-DPO-test

Updated 10 days ago