keypa/vision-adapter-embeddings download history

keypa/vision-adapter-embeddings is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 2,166 times (154 in the last 7 days), and 2,570 times in total. It ranks #10,620 among datasets by monthly downloads.

Vision Adapter MoonViT Embeddings Precomputed visual embeddings used to train lightweight vision→LLM projectors without re-running a vision tower: each row is the frozen MoonViT-V2 output for one training image, stored as raw bfloat16 bytes. Shards: 103 Parquet files (data/emb_0000.p

Open keypa/vision-adapter-embeddings on Hugging Face

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