snats
Joined 3 years ago
Karma
289
Submissions
93
Member since
Jul 13
snats.xyz
View on Hacker NewsRecent submissions
Comment · 5 months ago
did a pretty similar thing last month for the text rendering library last month.
trained and made a viz for the model and then made it displace text.
should probably do a proper write-up:https://x.com/i/status/2038367016969724259
Comment · 7 months ago
you can also have removed layers of models and keep the same score in benchmarks [1].
i feel that sometimes a lot of the layers might just be redundant and are not fully needed once a model is trained.
Comment · 9 months ago
personal website: snats.xyz
weblog: weblog.snats.xyz
Comment · 1 year ago
I also did a couple of experiments with pruning LLMs[1] using genetic algorithms and you can just keep removing a surprising amount of layers in big models before they start to have a stroke.
Comment · 1 year ago
i get it. i want one of those. the problem is that most cellphones are not actual cellphones, they are entertainment machines. they are a pocket tv / social media feed place. most usage for my normal friends is for that.