Add model card for OpenVision 2 with paper, project, code links, and pipeline tag
#1
by nielsr HF Staff - opened
This PR adds a comprehensive model card for the OpenVision 2 model.
It includes:
- A link to the paper: OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning.
- A link to the official project page: https://ucsc-vlaa.github.io/OpenVision2/.
- A link to the GitHub code: https://github.com/UCSC-VLAA/OpenVision/blob/main/src/main_openvision2.py.
- The
pipeline_tag: image-text-to-text, ensuring the model is discoverable under the correct task at https://huggingface.co/models?pipeline_tag=image-text-to-text. - The abstract of the paper for detailed information.
library_name and sample usage have been omitted due to the lack of explicit code evidence from the repository, adhering to the contribution guidelines.
Please review and merge if these additions are satisfactory.