Haoze Wu

WaitHZ's activity

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

commented 2 papers 5 months ago

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Paper • 2503.04598 • Published Mar 6 • 20 •

8

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Paper • 2503.04598 • Published Mar 6 • 20 •

8

commented a paper 7 months ago

Autonomy-of-Experts Models

Paper • 2501.13074 • Published Jan 22 • 45 •

5

New activity in deepseek-ai/deepseek-moe-16b-base over 1 year ago

A little question about aux_loss

2

#4 opened over 1 year ago by

WaitHZ

A little question about aux_loss

2

#4 opened over 1 year ago by

WaitHZ