Katherine

ksw1 's models 38

Sort:  Recently updated

ksw1/bert-probe-unsafe-reasoning

Text Classification • 0.1B • Updated Jun 3, 2025 • 2

ksw1/people_pleaser_v1

Text Generation • Updated Mar 6, 2025 • 5

ksw1/00001

Text Generation • 8B • Updated Jun 10, 2024 • 5

ksw1/DPO-3-1k-150steps-001

Text Generation • 8B • Updated Jun 10, 2024 • 5

ksw1/DPO-3-1k-25steps-001

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-25steps-nowarmup-smallbeta

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-159steps-nowarmup

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-25steps-nowarmup

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-2steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-1steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-5steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 7

ksw1/DPO-3-1k-10steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 11

ksw1/DPO-3-1k-25steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 9 •

ksw1/DPO-3-1k-250steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-300steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 6

ksw1/DPO-3-1k-300steps

Updated Jun 9, 2024

ksw1/DPO-3-1k-50steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-3-1k-150steps-2

Text Generation • 8B • Updated Jun 9, 2024 • 7

ksw1/DPO-3-1k-50steps

Updated Jun 9, 2024

ksw1/DPO-3-1k-150steps

Updated Jun 9, 2024

ksw1/DPO-3-10k

Text Generation • 8B • Updated Jun 9, 2024 • 6

ksw1/DPO-3-1k

Text Generation • 8B • Updated Jun 9, 2024 • 8

ksw1/DPO-2-10k

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-2-1k

Text Generation • 8B • Updated Jun 9, 2024 • 7

ksw1/DPO-1-1k

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/DPO-1-10k

Text Generation • 8B • Updated Jun 9, 2024 • 5

ksw1/step-375-1k-dpo3-2

Updated Jun 9, 2024

ksw1/DPO-3-1k-checkpoints-3

Updated Jun 9, 2024

ksw1/step-3500-10k-dpo3

Updated Jun 9, 2024

ksw1/DPO-3-10k-checkpoints

Updated Jun 9, 2024