Geyang's picture

Geyang

geyang627

·

AI & ML interests

None yet

Recent Activity

upvoted an article 7 days ago

Deriving the PPO Loss from First Principles

upvoted an article 7 days ago

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

new activity 4 months ago

QCRI/MultiNativQA:All is_reliable is True

View all activity

Organizations

liked a dataset 9 months ago

nvidia/HelpSteer3

Viewer • Updated Nov 16, 2025 • 133k • 4.34k • 98

liked 2 datasets 11 months ago

geyang627/CARE-eval

Viewer • Updated Jun 28, 2025 • 450 • 10 • 2

geyang627/CARE

Viewer • Updated Jun 28, 2025 • 28.1k • 53 • 3

liked 8 models 11 months ago

geyang627/care-arabic-qwen2.5-7b

8B • Updated Jun 30, 2025 • 2

geyang627/care-arabic-gemma2-9b

9B • Updated Jun 30, 2025 • 2

geyang627/care-arabic-llama3.1-8b

8B • Updated Jun 30, 2025 • 1

geyang627/care-chinese-qwen2.5-7b

8B • Updated Apr 8, 2025 • 70 • 1

geyang627/care-arabic-mistral-7b

7B • Updated Jun 30, 2025 • 1 • 1

geyang627/care-chinese-mistral-7b

7B • Updated Apr 8, 2025 • 3 • 1

geyang627/care-chinese-llama3.1-8b

8B • Updated Apr 8, 2025 • 2 • 1

geyang627/care-chinese-gemma2-9b

9B • Updated Apr 8, 2025 • 2 • 2

liked a dataset over 1 year ago

RUCAIBox/Erya-dataset

Updated Jul 24, 2023 • 77 • 9

liked 2 models over 1 year ago

RUCAIBox/Erya4FT

Translation • Updated Aug 3, 2023 • 23 • 4

RUCAIBox/Erya

Translation • Updated Aug 3, 2023 • 17 • 10

liked a dataset almost 2 years ago

RUCAIBox/SPA

Viewer • Updated May 5, 2024 • 17.3k • 96 • 2