CogVideo icon indicating copy to clipboard operation
CogVideo copied to clipboard

Published 20 hours ago • verified publisher icon THUDM

SFT doesn't support image joint training

Open jsg921019 opened this issue 4 months ago • 2 comments

Feature request / 功能建议

from the code of sat SFTDataset, i can only see it supports video dataset (mp4 extension), which is different from the paper that says uses images as well. Is there any reason for this?

Motivation / 动机

Motivation is curiousity and custom training. Thanks for sharing great model.

Your contribution / 您的贡献

None yet.

jsg921019 avatar Oct 21 '24 13:10 jsg921019