TinyVolt/multimodal-patch-embeddings

A ViT model that allows comparing text embeddings directly with image patch embeddings

3 best points · 0 comments · 1 Hacker News post · 13 GitHub stars · View on GitHub

Hacker News discussions

• Multimodal Image Patch Embeddings (3 points, 0 comments, by nivter, 2024-04-28)