Create and upload a Hugging Face model card
Evaluate RAG systems with visual analytics
Evaluate adversarial robustness using generative models
View and submit LLM benchmark evaluations
Compare code model performance on benchmarks
Measure execution times of BERT models using WebGPU and WASM
Generate leaderboard comparing DNA models
Leaderboard of information retrieval models in French
Browse and submit LLM evaluations
Calculate memory usage for LLM models
Display leaderboard for earthquake intent classification models
Request model evaluation on COCO val 2017 dataset
Measure over-refusal in LLMs using OR-Bench
Modelcard Creator is a tool designed to help users create and upload Hugging Face model cards. Model cards are essential for documenting and sharing machine learning models, providing details such as model architecture, performance metrics, and usage instructions. This tool simplifies the process of generating and managing model cards, making it easier for researchers and developers to showcase their models effectively.
• Model Card Creation: Easily generate model cards with pre-built templates.
• Hugging Face Compatibility: Directly upload your model card to the Hugging Face ecosystem.
• Documentation Generation: Automatically populate key sections like model description, evaluation results, and usage examples.
• Customization Options: Tailor your model card with specific details, visuals, and additional resources.
• Validation: Ensure your model card meets Hugging Face's guidelines and standards.
• Collaboration: Share and collaborate on model cards with team members.
• Version Control: Track changes and updates to your model cards over time.
• Accessibility: Designed for both novice and advanced users to streamline the model documentation process.
What is a model card?
A model card is a document that provides detailed information about a machine learning model, including its architecture, performance, and usage instructions. It serves as a transparency tool for AI models.
What information do I need to create a model card?
You need details such as the model's name, description, architecture, evaluation metrics, and usage examples. Optional sections may include visualizations or citations.
Where can I find help if I encounter issues?
You can refer to the Hugging Face documentation or contact support for assistance with creating or uploading your model card.