Guoqing Luo's picture

3 5 1

Guoqing Luo

frankdarkluo

·

frankdarkluo

AI & ML interests

NLP

Recent Activity

updated a dataset 5 days ago

frankdarkluo/BBQ

published a dataset 6 days ago

frankdarkluo/BBQ

upvoted a paper 11 days ago

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

View all activity

Organizations

None yet

models 2

frankdarkluo/SFT-StableBeluga-7B

Text Generation • Updated Jan 8, 2024 • 1

frankdarkluo/DPO-StableBeluga-7B

Text Generation • 7B • Updated Dec 1, 2023

datasets 3

frankdarkluo/BBQ

Viewer • Updated 5 days ago • 3.79k • 32

frankdarkluo/DailyDialog

Viewer • Updated May 13, 2024 • 73.6k • 141 • 7

frankdarkluo/OpenSubtitles

Viewer • Updated May 13, 2024 • 1M • 32