gfodor / instructblip
Image captioning via vision-language models with instruction tuning
-
ca869b56b2a3b1cdf591c353deb3fa1a94b9c35fde477ef6ca1d248af56f9c84pushed 4 months, 1 week ago
- Version
- 22.04
-
e4b3b77cb6df96ba5c893c757b6960c7335d9e49e23d6a54af4414e4d49532f4pushed 4 months, 1 week ago
- Version
- 22.04