Xingyu Shen

xingyushenai's activity

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

upvoted a collection 4 days ago

Competing Learning Models

Collection

Vanilla and BLD KDA hybrid language models from Competing Learning in Hybrid Architectures (250M–1B parameters). • 10 items • Updated 20 days ago • 1

upvoted a collection 12 days ago

HypeNet

Collection

The models for the paper: Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts • 2 items • Updated Apr 28