Ablations
Collection
playing with k and rho
•
27 items
•
Updated
Model Initialized from openai/clip-vit-large-patch14. The image encoder is finetuned with FARE at $\epsilon=2/255$.
To load this model use:
from transformers import CLIPProcessor, CLIPModel
model_name = "LEAF-CLIP/CLIP-ViT-L-FARE2"
processor_name = "openai/clip-vit-large-patch14"
model = CLIPModel.from_pretrained(model_name)
processor = CLIPProcessor.from_pretrained(processor_name)
- Downloads last month
- 192
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for LEAF-CLIP/CLIP-ViT-L-FARE2
Base model
openai/clip-vit-large-patch14