Geyang

geyang627's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

Safe and Scalable Web Agent Learning via Recreated Websites

Paper • 2603.10505 • Published 8 days ago • 22

upvoted 2 articles 16 days ago

view article

Article

Deriving the PPO Loss from First Principles

• 

Dec 25, 2025

•

38

view article

Article

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

• 

Jan 19

•

10

New activity in QCRI/MultiNativQA 4 months ago

All is_reliable is True

1

#2 opened 4 months ago by

geyang627

upvoted a collection 7 months ago

Qwen3

Collection

84 items • Updated Dec 31, 2025 • 1.72k

updated 3 models 9 months ago

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

8B • Updated Jun 30, 2025 • 5 • 2

geyang627/care-arabic-gemma2-9b

9B • Updated Jun 30, 2025 • 2

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

8B • Updated Jun 30, 2025 • 17 • 1

updated a collection 9 months ago

CARE

Collection

14 items • Updated Jun 30, 2025 • 2

updated 5 models 9 months ago

geyang627/care-arabic-mistral-7b

7B • Updated Jun 30, 2025 • 1

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

8B • Updated Jun 28, 2025 • 11

geyang627/care-japanese-mistral-7b

7B • Updated Jun 28, 2025 • 1 • 1

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

8B • Updated Jun 28, 2025 • 14 • 1

geyang627/care-japanese-gemma2-9b

9B • Updated Jun 28, 2025 • 4 • 1

published 3 models 9 months ago

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

8B • Updated Jun 28, 2025 • 11

geyang627/care-japanese-mistral-7b

7B • Updated Jun 28, 2025 • 1 • 1

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

8B • Updated Jun 28, 2025 • 14 • 1