Giang Do PRO

tataredmi

1

·

AI & ML interests

None yet

Recent Activity

upvoted an article 23 days ago

Deriving the DPO Loss from First Principles

updated a model 3 months ago

tataredmi/rlvr-countdown-v6H

published a model 3 months ago

tataredmi/rlvr-countdown-v6H

View all activity

Organizations

tataredmi 's models 4

tataredmi/rlvr-countdown-v6H

tataredmi/Qwen3-0.6B-Full-Finetuning

Text Generation • 0.6B • Updated May 6 • 18

tataredmi/Qwen3-0.6B-Base-CPT-Math

Text Generation • 0.6B • Updated May 3 • 16

tataredmi/smollm3-unit1-fullft

Text Generation • 3B • Updated Feb 6 • 18