Horace He(@cHHillee):It truly takes a village to release a model, perhaps especially an open weights model. Actually doing the entire process from scratch, from data to pretraining to posttraining to actual release, gives a lot of appreciation for anyone who does it! There's so many places to go wrong, and indeed so many things we would (and will!) do differently for a new model. But I'm happy with where we ended up :) Onto what's next!

Horace He

@cHHillee

@thinkymachines Formerly @PyTorch "My learning style is Horace twitter threads" - @typedfemale

가입 February 2010

606 팔로잉 중 52.6K 팬

Horace He@cHHillee

2026.07.15 18:18

It truly takes a village to release a model, perhaps especially an open weights model. Actually doing the entire process from scratch, from data to pretraining to posttraining to actual release, gives a lot of appreciation for anyone who does it! There's so many places to go wrong, and indeed so many things we would (and will!) do differently for a new model. But I'm happy with where we ended up :) Onto what's next!

1.3K

커뮤니티로 전달

인기 있는 사용자