shijiay
/

llava_openclip_stage2

Image-Text-to-Text

text-generation

Inference Endpoints

Model card Files Files and versions Community

llava_openclip_stage2 / README.md

shijiay's picture

Create README.md

7bd0ac3 verified 2 months ago

|

166 Bytes

This model is the stage 2 checkpoint of one of the thirteen settings, OpenCLIP, used in the Law of Vision Representation in MLLMs.