Zikang Shan's picture

Zikang Shan PRO

zkshan2002

·

https://zkshan2002.github.io/

zkshan2002

AI & ML interests

Reinforcement Learning

Recent Activity

updated a model 8 minutes ago

zktmp/dq2e-format0-4-step64

published a model 9 minutes ago

zktmp/dq2e-format0-4-step64

updated a model about 23 hours ago

zktmp/dq2e-format0-2-step102

View all activity

Organizations

Collections 2

models 6

zkshan2002/rm-lsft0

8B • Updated 10 days ago • 17

zkshan2002/rm-lsft

8B • Updated 15 days ago • 116

zkshan2002/rm-q3

8B • Updated 15 days ago • 75

zkshan2002/dl2025_adaptive

8B • Updated Jun 25 • 10

zkshan2002/dl2025_filter

8B • Updated Jun 21 • 8

zkshan2002/dl2025_grpo

8B • Updated Jun 19 • 9

datasets 32

zkshan2002/rstar2a

Viewer • Updated 7 days ago • 42.3k • 77

zkshan2002/alpaca_eval

Viewer • Updated 13 days ago • 805 • 158

zkshan2002/ultrafeedback_binarized

Viewer • Updated 17 days ago • 63.1k • 225

zkshan2002/simple_rl_level1to4

Viewer • Updated 20 days ago • 8.64k • 88

zkshan2002/simple_rl_level3to5

Viewer • Updated 20 days ago • 9.02k • 90

zkshan2002/dr_sft

Viewer • Updated about 1 month ago • 5.91k • 132

zkshan2002/prime_sft

Viewer • Updated about 1 month ago • 5.58k • 97

zkshan2002/prime_full

Viewer • Updated about 1 month ago • 456k • 69

zkshan2002/dr_full

Viewer • Updated about 1 month ago • 40.3k • 337

zkshan2002/dr_sft_legacy

Viewer • Updated Aug 8 • 6.03k • 70

View 32 datasets