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

That all being said, you can just delete the T5 from memory after encoding the text so save on memory.

The 2B parameters will take up 4 Gb of memory but activations will be a lot more given size of context windows for video.

A 720p 5 second video is roughly 100K tokens of context



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: