Instructions to use RISys-Lab/ReasonCLIP-B32-S1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RISys-Lab/ReasonCLIP-B32-S1 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-S1") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("RISys-Lab/ReasonCLIP-B32-S1") model = AutoModelForZeroShotImageClassification.from_pretrained("RISys-Lab/ReasonCLIP-B32-S1") - Notebooks
- Google Colab
- Kaggle
Add model card, paper link, license, and usage example
#1
by nielsr HF Staff - opened
Hi! I'm opening this PR to replace the placeholder model card with a documented model card for ReasonCLIP.
Specifically, this PR:
- Adds the
pipeline_tag: zero-shot-image-classificationandlicense: cc-by-nc-sa-4.0(Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International) to the metadata. - Links the model card to the paper ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP.
- Adds a link to the official GitHub repository (https://github.com/RISys-Lab/ReasonCLIP).
- Includes the
transformersQuick Start code snippet provided in the repository's README.
Let me know if you have any questions or feedback!