LLaVA-NeXT
LLaVA-NeXT copied to clipboard
Where to find multi-image training data?
Hi, I can only find a subset of the image from the dataset in huggingface
And I don't find multi-image datas in the dataset. for example, tqa is a multi-image dataset, but the specific items in this dataset have only one image.
Did I use the dataset in a wrong way?