When's picture

9 15

When

WhenceFade

·

https://mufan.me

WhenMelancholy

AI & ML interests

Generative Models.

Recent Activity

upvoted a paper 2 days ago

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss

updated a dataset about 1 month ago

WhenceFade/dataset-mix-cached

updated a dataset about 1 month ago

WhenceFade/dataset-mix-cached

View all activity

Organizations

WhenceFade 's datasets 12

WhenceFade/0604_key_cache_dynamic_qwen3

Viewer • Updated Jun 4, 2025 • 1.57M • 23 • 1

WhenceFade/0604_key_cache_dynamic_qwen

Viewer • Updated Jun 4, 2025 • 1.57M • 14

WhenceFade/0601_key_cache_dynamic_olmoe

Viewer • Updated Jun 2, 2025 • 1.57M • 28

WhenceFade/0529_key_cache_dynamic_olmoe

Viewer • Updated May 29, 2025 • 1.52M • 23

WhenceFade/0528_key_cache_dynamic_olmoe

Viewer • Updated May 29, 2025 • 1.52M • 12

WhenceFade/0424_key_cache_dynamic_olmoe

Viewer • Updated Apr 24, 2025 • 1.2M • 17

WhenceFade/key_cache_olmoe

Viewer • Updated Apr 10, 2025 • 14.7k • 10

WhenceFade/minipile_olmoe

Viewer • Updated Mar 12, 2025 • 1.01M • 25

WhenceFade/lima_safe_olmoe

Viewer • Updated Mar 11, 2025 • 3.81k • 10

WhenceFade/key_olmoe

Viewer • Updated Mar 7, 2025 • 1.66M • 39

WhenceFade/lima_olmoe

Viewer • Updated Feb 26, 2025 • 1.33k • 7

WhenceFade/dataset-mix-cached

Updated Feb 25, 2025 • 1