shijiay
/

llava_clip224_stage1

Image-Text-to-Text

text-generation

Inference Endpoints

Model card Files Files and versions Community

llava_clip224_stage1 / README.md

shijiay's picture

Create README.md

c6135f9 verified 4 months ago

|

166 Bytes

This model is the stage 1 checkpoint of one of the thirteen settings, CLIP@224, used in the Law of Vision Representation in MLLMs.