Haiyang Wang

Haiyang-W's activity

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

updated a model 2 days ago

Haiyang-W/TokenFormer-354M-Openwebtext2

Updated 2 days ago

upvoted 10 collections about 2 months ago

Papers - Attention - Token Parameter - Pattention

Collection

1 item • Updated Nov 2, 2024 • 1

paper list

Collection

3 items • Updated Nov 4, 2024 • 1

daily-papers

Collection

100 items • Updated 17 days ago • 3

Model Architecture

Collection

3 items • Updated Nov 4, 2024 • 1

Papers

Collection

261 items • Updated 1 day ago • 7

Papers - Google

Collection

53 items • Updated Nov 2, 2024 • 1

Papers - Custom Layers

Collection

25 items • Updated 1 day ago • 2

Papers - Attention - Cross

Collection

17 items • Updated 12 days ago • 1

paper2read

Collection

118 items • Updated 6 days ago • 2

interesting stuff

Collection

110 items • Updated 16 days ago • 2

updated 4 models about 2 months ago

Haiyang-W/TokenFormer-1-5B

Text Generation • Updated Nov 9, 2024 • 26 • 11

Haiyang-W/TokenFormer-900M

Updated Nov 9, 2024 • 1 • 2

Haiyang-W/TokenFormer-450M

Updated Nov 9, 2024 • 2 • 1

Haiyang-W/TokenFormer-150M

Updated Nov 9, 2024 • 16 • 1

New activity in Haiyang-W/TokenFormer-1-5B 2 months ago

Add pipeline tag

#1 opened 2 months ago by

nielsr

authored a paper 2 months ago

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Paper • 2410.23168 • Published Oct 30, 2024 • 24

upvoted a paper 2 months ago

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Paper • 2410.23168 • Published Oct 30, 2024 • 24

commented a paper 2 months ago

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Paper • 2410.23168 • Published Oct 30, 2024 • 24 •

5

liked a model 2 months ago

Haiyang-W/TokenFormer-1-5B

Text Generation • Updated Nov 9, 2024 • 26 • 11