dingshizhe/molmo-ae-cc12m-latents download history

dingshizhe/molmo-ae-cc12m-latents is a text to image dataset on the Hugging Face Hub. In the last 30 days it was downloaded 522 times (174 in the last 7 days), and 924 times in total. It ranks #32,156 among datasets by monthly downloads.

CC12M latents — VGT-AE with a frozen SigLIP2 (Molmo) encoder Pre-encoded CC12M images as (32, 16, 16) float16 latents, paired with their captions. WebDataset format: 1097 tars, each member a <key>.npy + <key>.txt pair. samples 6,836,022 shards 1097 latent shape (32, 1

Open dingshizhe/molmo-ae-cc12m-latents on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.