File size: 214 Bytes
d0608e4
 
 
bcb382b
1
2
3
4
---
pipeline_tag: image-text-to-text
---
This model is the stage 1 checkpoint of one of the thirteen settings, CLIP+DINOv2@224, used in the [Law of Vision Representation in MLLMs](https://arxiv.org/abs/2408.16357).