Instructions to use RISys-Lab/ReasonCLIP-B32-READ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RISys-Lab/ReasonCLIP-B32-READ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="RISys-Lab/ReasonCLIP-B32-READ") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("RISys-Lab/ReasonCLIP-B32-READ") model = AutoModelForZeroShotImageClassification.from_pretrained("RISys-Lab/ReasonCLIP-B32-READ", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
docs: add playground link
Verified signature4187c10
-
docs: add project and paper links
Verified signature70333cf -
docs: correct license metadata to CC BY-NC-SA 4.0
Verified signature2b09242 -
docs: add CC BY-SA 4.0 license metadata
Verified signaturecb7c9b0
-
Upload processor
Verified signature76e1a75 -
Copy weights from fesvhtr/clip-r-b32-s1-read
Verified signaturef117fc2 -
initial commit
Verified signaturea74001f