Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: Text-to-video model from scratch (2 brothers, 2 years, 2B params). Parent comment
When we started down this path, T5 was the standard (back in 2024).
Likely won’t be the text encoder for subsequent models, given its size (per your point) and age
There are no comments on this comment yet.
When we started down this path, T5 was the standard (back in 2024).
Likely won’t be the text encoder for subsequent models, given its size (per your point) and age