Your models might be ridiculously tiny, but a lot of people's models are not. Ta... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Eridrus on May 9, 2020 \| parent \| context \| favorite \| on: Researchers unveil a pruning algorithm to shrink ... Your models might be ridiculously tiny, but a lot of people's models are not. Take a loot at any research paper in vision, speech or language. The models are gigantic.

natch on May 9, 2020 [–]

But quantization solves the problem of models being gigantic. So the question is still unanswered. But hey, you got in your downvote, thanks for that.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact