Browse Definitions :

model card in machine learning

What is a model card in machine learning?

A model card is a type of documentation that is created for, and provided with, machine learning models. A model card functions as a type of data sheet, similar in principle to the consumer safety labels, food nutritional labels, a material safety data sheet or product spec sheets.

There has been a dramatic rise in the development and adoption of machine learning (ML) and artificial intelligence (AI) during recent years. Further advances in generative AI employ large language models (LLMs) as a core component. However, the many models used in those platforms are increasingly complex and difficult to understand. Even model developers sometimes struggle to fully understand and describe the ways a given model behaves. This complexity has created serious questions about core business values such as transparency, ethics and accountability. Common questions include the following:

  • What is a particular ML model used for?
  • How does a particular ML model work or perform?
  • What training data was used to train the model (and what were the results)?

First proposed by Google in 2018, the model card is a means of documenting vital elements of a ML model so users -- including AI designers, business leaders and ML end users -- can readily understand the intended use cases, characteristics, behaviors, ethical considerations, and the biases and limitations of a particular ML model.

As late as 2024, there are no current legislative or regulatory requirements to produce or provide model card documentation with ML models. Similarly, there are no currently established standards in model card format or content. However, major ML developers have spearheaded the adoption of model card documentation as a way of demonstrating responsible AI development, and adopters can find model cards for major platforms such as Meta Llama, Google face detection and OpenAI GPT-3.

Benefits of using model cards for AI, ML and LLM projects

The rise of ML and AI is driving the need for transparency and responsible governance. Businesses must understand what ML models are for, how they work, how they compare to other competitive models, how they're trained and their suitability for intended tasks.

Model cards are a tool that can address such concerns which readily impact governance and regulatory issues for the business. Model cards can provide a range of important benefits to ML and AI projects including the following:

  • Model selection. By adopting a consistent standard for format and content, model cards can help ML and AI developers evaluate and select the most appropriate ML model for the project. Model cards can help whittle down an initial list of ML candidates, focus testing and evaluation on the most appropriate models, and accelerate final selection of the best ML model for the task at hand.
  • Model behavior and performance. ML models are not perfect, and limitations in the training data sets or biases in the training methodologies can impact the model's behavior when dealing with real-world data. Model cards typically include known limitations in data and training, allowing ML model users to see and address such limitations through additional training and data. This can help the business reduce errors and biases in the ML model and improve AI project performance and outcomes.
  • Continued AI improvements. The details and information provided by ML model cards help businesses select the most appropriate models and allow ML model developers to compare their models to others to make platforms more capable and competitive. This leads to more innovation and improvements to ML models and the resulting ML and AI platforms that use those models.
  • Business governance. The old axiom "you can't manage what you can't see" is entirely appropriate for modern ML models. A business that employs opaque or incomprehensible ML models cannot understand or explain the behavior of their developing ML or AI project-- risking serious business continuance, business governance and regulatory compliance violations. ML model cards are a means for the business to demonstrate an understanding of the underlying ML models that they select and use.
  • Business transparency and ethics. ML and AI technologies have an impact on society -- both in the collected and used data and in the ways that data is processed to make decisions. The documentation and details provided in ML model cards can help a business manage responsible AI development and address social concerns regarding the organization's use of AI and underlying data.

7 key sections of a model card

Labels and other informational summaries are generally most effective when they allow comparing similar products side by side using comparable content and formats. However, the information presented on an ML model card can vary. Unlike highly regulated informational displays -- such as food nutritional labeling -- there are no current standards to govern the information or formatting included on ML model cards.

ML models can vary dramatically in their scope, purpose and capabilities, so this makes it hard to regulate. For example, an ML model developed to aid in medical diagnosis can be distinctly different than an ML model created to run analytics on retail sales operations, or a complex LLM used in an AI construct. Consequently, ML model developers largely use their own discretion to determine what information to include, and how that information should be presented. Yet, as leading technology firms develop ML/AI platforms and document those offerings through model cards, some de facto documentation standards are taking shape. Model cards should include the following:

1. Basic details

This first section of a model card is typically the introduction to the model which can outline the model's essential details including the model's name, version, revision list, a brief general description of the model, business or developer details and contact information, and licensing details or limits.

2. Use case details

This section describes the intended uses, use cases and users for the model. For example, a section on use cases may describe uses in object detection, facial detection or medical diagnoses. This section may also include caveats, use limitations or uses deemed out of scope. For example, a model intended for object detection may detail input from photos or video; output including detection of a specified number of object classes; and other output data such as object bounding box coordinates, knowledge graph ID, object description and confidence score.

3. Architectural details

This section describes the overall design of the model and any underlying hardware back end that runs the model and hosts related data. Readers can refer to the model card to understand the design elements or underlying technologies that make the model work. For the object detection model example, the model card may describe an architecture including a single image detector model with a Resnet 101 backbone and a feature pyramid network feature map.

4. Training details

This section outlines, describes or summarizes the data used in model training; where and when the data was obtained; and any statistical distribution of key factors in the data which may allow for inadvertent bias. Since training data may be proprietary to the model's developers, training details may be deliberately limited or protected by a separate confidentiality agreement. Training details may also describe training methodologies employed with the model.

5. Performance details

This section outlines details related to the model's performance measured against a test data set, not a training data set, as well as details about the test data set itself. For the object detection model example, performance metrics included on the model card may note the use of both Google's internal image data set as well as an open source image set as test data and the number of object classes the model can detect in each data set. Additionally, performance details may outline reported metrics including the precision and accuracy of the object detection. More sophisticated models may utilize other detailed metrics to measure performance.

6. Limitation details

A key segment of any model card is the section describing limitations, possible biases or variable factors that might affect the model's performance or output. For the object detection model example, known limitations may include factors such as object size, clutter, lighting, blur, resolution and object type since the model can't recognize everything.

7. Business details

This final segment of a model card is often dedicated to business-related details including information about the model's developers, detailed contact, support and licensing information, fairness/privacy and usage information, suggestions for model monitoring, any relevant assessment of impacts to individuals or society, and other ethical or potential legal concerns related to the model's usage.

Examples of model cards

As leading technology organizations build ML and AI platforms, their work on model cards and other documentation has provided a standard for other ML firms to follow. Today there are many examples of ML model cards to review including the following major examples:

  • Google's face detection model card.
  • Meta's Llama model card.
  • OpenAI's GPT-3 model card.

There are also more standardized tools for model card creation, as well as model card repositories, such as these examples:

Both GitHub and Hugging Face provide a repository of model cards which are available for review and study, offering model card examples across many different model types, purposes and industry segments.

This was last updated in March 2024

Continue Reading About model card in machine learning

  • personally identifiable information (PII)

    Personally identifiable information (PII) is any data that could potentially identify a specific individual.

  • zero-day vulnerability

    A zero-day vulnerability is a security loophole in software, hardware or firmware that threat actors exploit before the vendors ...

  • DNS attack

    A DNS attack is an exploit in which an attacker takes advantage of vulnerabilities in the domain name system.

  • data collection

    Data collection is the process of gathering data for use in business decision-making, strategic planning, research and other ...

  • chief trust officer

    A chief trust officer (CTrO) in the IT industry is an executive job title given to the person responsible for building confidence...

  • green IT (green information technology)

    Green IT (green information technology) is the practice of creating and using environmentally sustainable computing resources.

  • diversity, equity and inclusion (DEI)

    Diversity, equity and inclusion is a term used to describe policies and programs that promote the representation and ...

  • ADP Mobile Solutions

    ADP Mobile Solutions is a self-service mobile app that enables employees to access work records such as pay, schedules, timecards...

  • director of employee engagement

    Director of employee engagement is one of the job titles for a human resources (HR) manager who is responsible for an ...

Customer Experience
  • digital marketing

    Digital marketing is the promotion and marketing of goods and services to consumers through digital channels and electronic ...

  • contact center schedule adherence

    Contact center schedule adherence is a standard metric used in business contact centers to determine whether contact center ...

  • customer retention

    Customer retention is a metric that measures customer loyalty, or an organization's ability to retain customers over time.