ostris
/

CLIP-H-Face-v3

clip_vision_model

Inference Endpoints

Model card Files Files and versions Community

Edit model card

This is just the vision encoder from CLIP-ViT-H-14-laion2B-s32B-b79K but it has been slightly tuned on just faces.

Downloads last month: 3

Safetensors

Model size

632M params

Tensor type

FP16

·

Unable to determine this model’s pipeline type. Check the docs .