zheedong

Results 3 issues of zheedong

Thank you for your great work. I want to download your dataset, but download link (Google drive, OneDrive) is not available. Where I can get them? Thank you.

Hi, in tokenizer training, you apply blocks for reconstruction causal embedding, and apply blocks_for_image (in 'blip2_qformer_codebook_all_image.py'). But you apply only blocks in get_codebook_indicies (in 'qformer_quantizer.py'). Why is it difference here?

Thanks for your great work. In paper, you say that training data of tokenizer is 'CC3M, Unsplash, LAION-COCO, MS-COCO'. Did you use total of those three dataset? Or did you...