Video yükleniyor...
Video Yüklenemedi
llama 4 maverick do visually look stunning.
62,407 görüntüleme • 1 yıl önce •via X (Twitter)
10 Yorum

losh1 yıl önce
a little explanation of what you are seeing here. The models when stored have a structure (not execution graph, just how parameters are grouped). the color coding represent types of param blocks and the block size is log(param_size). I did similar plots in 2d sometime back:

Viraat1 yıl önce
This is really cool - in a few months if you are looking for a job and are interested hmu

losh1 yıl önce
sure, and thanks!

Krishna Mohan1 yıl önce
Amazing

⛓️☆ ilex ☆⛓️1 yıl önce
I like how this feels in my brain

losh1 yıl önce
latest

ueaj1 yıl önce
It might look cooler if experts are separate squares, like a grid or something

Louis1 yıl önce
wow

deep Manifold1 yıl önce
Really cool

Karan Lokchandani1 yıl önce
im never deleting this app


