Model card is a
README.md file that accompanies the model to describe handy information with additional model metadata. Under the hood, a Model card is associated with every model instance of a model.
It is an crucial for reproducibility, sharing and discoverability. We highly recommend adding a model card
README.md file when preparing your model used in VDP.
In a model card, you can provide information about:
- the model itself
- its use cases and limitations
- the datasets used to train the model
- the training experiments and configuration
- benchmarking and evaluation results
- reference materials
After importing a model into VDP, the model card will be rendered in the Console on the Model page. Here shows a model card example of a model imported from a GitHub repository model-mobilenetv2.
Try our Import GitHub models guideline to import a model from GitHub
#Model card metadata
You can insert Front Matter in a model card to define the model metadata.
Start with three
--- at the top, then include all the metadata and close the section with
--- like the example below.
#Specify an AI task
Technically, you can assign different AI task to model instances of the same model. However, this is strongly discouraged. Model instances of a model should be designed to solve the same task.
When importing the model, VDP will detect the
Task in the model card and verify if output of the model fulfils the AI task requirements.
If the model is verified, VDP will automatically convert the model output into format of the corresponding standardised AI task format whenever using the model.
Please check the supported standarised AI tasks and the corresponding output format for each task.
If not specified, the model will be recognised with
Unspecified AI task,
and the raw model output will be wrapped in a standard format.
❓ How to know if the AI task metadata is correctly recognised?
If you include valid AI task metadata, they will show on the Model page of the Console like this: