Instructions to use UCSC-VLAA/openvision3-vit-large-patch2-32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use UCSC-VLAA/openvision3-vit-large-patch2-32 with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:UCSC-VLAA/openvision3-vit-large-patch2-32') tokenizer = open_clip.get_tokenizer('hf-hub:UCSC-VLAA/openvision3-vit-large-patch2-32') - Notebooks
- Google Colab
- Kaggle
Add model card for OpenVision 3
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community science team.
This pull request adds a model card for OpenVision 3. It includes:
- Metadata for
pipeline_tag,library_name, andlicense. - A description of the model architecture and its unified representation for understanding and generation.
- Links to the paper, project page, and official GitHub repository.
- A sample usage snippet using the
open_cliplibrary. - The appropriate citation for the research.