You can deploy this model and start earning money today!

LEAF-CLIP/
OpenCLIP-ViT-g-rho50-k1-FARE2

Name: OpenCLIP-ViT-g-rho50-k1-FARE2
Availability: InStock

safetensors

clip

ILSVRC/imagenet-1k

mlfoundations/datacomp_small

laion/CLIP-ViT-g-14-laion2B-s12B-b42K

finetune

mit

Views

No views yet

Model Initialized from laion/CLIP-ViT-g-14-laion2B-s12B-b42K. The image encoder is finetuned with FARE at $\epsilon=2/255$. The text encoder is finetuned with LEAF at $k=1$ with $\rho=50$.

To load this model use:

python

from transformers import CLIPProcessor, CLIPModel

model_name = "LEAF-CLIP/OpenCLIP-ViT-g-rho50-k1-FARE2"
processor_name = "laion/CLIP-ViT-g-14-laion2B-s12B-b42K"

model = CLIPModel.from_pretrained(model_name)
processor = CLIPProcessor.from_pretrained(processor_name)