Update model card for D2E: Add metadata, links, image, and sample usage
#1
by
nielsr
HF Staff
- opened
This PR significantly improves the model card for the D2E model by:
- Adding
pipeline_tag: roboticsto categorize the model accurately, as it focuses on embodied AI and robotics tasks. - Including
library_name: transformersto enable the "how to use" widget, as evidenced by the sample code in the GitHub README. - Providing a link to the official paper: D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI.
- Adding a link to the project page: https://worv-ai.github.io/d2e/.
- Including a link to the GitHub repository: https://github.com/worv-ai/D2E.
- Adding an illustrative image from the GitHub README.
- Adding a detailed sample usage code snippet directly from the GitHub README for easy replication.
Please review and merge this PR.
Hi! Thanks for the PR. This Generalist IDM operates differently from a standard Hub VLM model, so it cannot run without our custom inference code. We are planning to publish a model card, the inference code, and an HF Space demo next week. I’ll keep it in mind for your suggestion when writing the model card.
Thanks! Would be great to add the paper link and metadata tags