Enhance model card for Large Video Planner Enables Generalizable Robot Control
#1
by
nielsr
HF Staff
- opened
This PR significantly enhances the model card for the "Large Video Planner Enables Generalizable Robot Control" model by adding crucial metadata, relevant links, and a clear usage example, while retaining and reformatting existing valuable information.
Key updates include:
- Metadata: Added
pipeline_tag: roboticsandlicense: apache-2.0for improved discoverability and categorization on the Hugging Face Hub. - Overview: A concise introduction summarizing the model's purpose and capabilities, derived from the paper's abstract.
- Links: Incorporated direct links to the official Hugging Face paper page, the project webpage, the GitHub repository, and the Hugging Face Demo Space.
- Sample Usage: Included a runnable bash code snippet for inference, directly sourced from the GitHub repository's
READMEto ensure accuracy and ease of use. - Content Structure: Existing details about trained checkpoints, dataset format, and dataset downloading instructions have been retained and organized with proper Markdown headings for better readability.
These improvements aim to make the model card more informative, user-friendly, and aligned with Hugging Face Hub best practices.
Reviewed and looks good.
timothyngo
changed pull request status to
merged