# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForZeroShotImageClassification
processor = AutoProcessor.from_pretrained("PS4Research/marimo-workshop-clip")
model = AutoModelForZeroShotImageClassification.from_pretrained("PS4Research/marimo-workshop-clip", device_map="auto")Quick Links
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.
- Downloads last month
- 27
Model tree for PS4Research/marimo-workshop-clip
Base model
openai/clip-vit-base-patch32
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="PS4Research/marimo-workshop-clip") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )