Yunjae Won

yunjae-won's activity

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

updated a model 17 days ago

yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001

Text Generation • 0.5B • Updated 17 days ago • 272

published 2 models 17 days ago

yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001

Text Generation • 0.5B • Updated 17 days ago • 272

yunjae-won/ubq30i_qwen4b_dpo_topk20_j0

Text Generation • 0.5B • Updated 17 days ago • 284

updated a dataset 17 days ago

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

Viewer • Updated 17 days ago • 12 • 35

published a dataset 17 days ago

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

Viewer • Updated 17 days ago • 12 • 35

updated a model 17 days ago

yunjae-won/ubq30i_qwen4b_dpo_topk20_j0

Text Generation • 0.5B • Updated 17 days ago • 284

updated a dataset 17 days ago

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

Viewer • Updated 17 days ago • 60.9k • 44

published a dataset 17 days ago

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

Viewer • Updated 17 days ago • 60.9k • 44

updated a model 18 days ago

yunjae-won/ubq30i_qwen4b_sft_both

Text Generation • 4B • Updated 18 days ago • 1.07k

published a model 18 days ago

yunjae-won/ubq30i_qwen4b_sft_both

Text Generation • 4B • Updated 18 days ago • 1.07k

updated a model 18 days ago

yunjae-won/ubq30i_qwen4b_sft_yw

Text Generation • 4B • Updated 18 days ago • 548

published a model 18 days ago

yunjae-won/ubq30i_qwen4b_sft_yw

Text Generation • 4B • Updated 18 days ago • 548

updated a model 18 days ago

yunjae-won/ubq30i_qwen4b_sft_yl

Text Generation • 4B • Updated 18 days ago • 541

published 3 models 18 days ago

yunjae-won/ubq30i_qwen4b_sft_yl

Text Generation • 4B • Updated 18 days ago • 541

yunjae-won/ub_qwen4Bi_onlineDPO-w1e-2

Updated 18 days ago

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

Updated 18 days ago

published 3 models 19 days ago

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

Updated 19 days ago

yunjae-won/ub_qwen0.5Bi_onlineDPO-test

Updated 19 days ago

yunjae-won/ubq30i_qwen4b_sft-Online-DPO-test

Updated 19 days ago

published a model 20 days ago

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

Updated 20 days ago