# Load model directly
from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection
processor = AutoProcessor.from_pretrained("fxmarty/owlvit-tiny-non-contiguous-weight")
model = AutoModelForZeroShotObjectDetection.from_pretrained("fxmarty/owlvit-tiny-non-contiguous-weight", device_map="auto")Quick Links
Real models as google/owlvit-base-patch16 have non-contiguous weights in their state dict. This is for testing purposes.
- Downloads last month
- 203
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-object-detection", model="fxmarty/owlvit-tiny-non-contiguous-weight")