CLIP ViT-B/32 for the marimo workshop
An unmodified copy of openai/clip-vit-base-patch32 (revision 3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268),
saved as safetensors with its pre-processor. It is pinned here so every workshop notebook loads exactly the same
weights that produced the vectors in
PS4Research/marimo-workshop-catalogue.
from transformers import CLIPModel, CLIPProcessor
model = CLIPModel.from_pretrained("PS4Research/marimo-workshop-clip")
processor = CLIPProcessor.from_pretrained("PS4Research/marimo-workshop-clip")
No fine-tuning was done. See the original model card for intended uses, limitations and biases.