|
|
|
|
|
|
by schopra909
142 days ago
|
|
|
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 |
|
|