shijiay
/

llava_clip_stage2

Image-Text-to-Text

text-generation

Inference Endpoints

Model card Files Files and versions Community

llava_clip_stage2 / README.md

shijiay's picture

Update README.md

73c3cc1 verified 4 months ago

|

207 Bytes

metadata

pipeline_tag: image-text-to-text

This model is the stage 2 checkpoint of one of the thirteen settings, CLIP@336, used in the Law of Vision Representation in MLLMs.