Transformers have quickly become the go-to architecture for natural language processing (NLP). As a result, knowing how to use them is now a business-critical skill in your AI toolbox. In this course, instructor Jonathan Fernandes walks you through many of the key large language models (LLMs) developed since OpenAI first released GPT-3, as well as the key contributions of each of these LLMs.
Learning objectives
- Identify the release dates of large language models.
- Interpret actions needed to successfully run large language models.
- Differentiate several types of large language models.
- Assess the capabilities of several large language models.
- Discover key contributions of large language models.
- Determine the role that scaling laws have in each large language model.
Machine Learning Operations (MLOps) is a fast-growing domain the field of AI. As more models are deployed in production, the need for a structured, agile, end-to-end ML lifecycle with automation has grown multifold. MLOps provides structure to machine learning projects and help them succeed over the long run. In this course, instructor Kumaran Ponnambalam focuses on the key concepts of MLOps and helps you apply these concepts to your day-to-day ML work. Kumaran introduces you to the machine learning life cycle and explains unique challenges with ML, as well as important definitions and principles. He walks you through the requirements and design for ML projects, then dives into data processing and management. Kumaran explains various tools and technologies that you can use in the automation and management of continuous training. He covers best practices for model management, then offers detailed instruction on continuous integration.
Learning objectives
- List the main components of the machine learning lifecycle.
- Define MLOps and explore the MLOps lifecycle in greater detail.
- Identify the main principles of MLOps.
- Explore basic feature validation, data distribution validation, and out-of-distribution validation.
- Define the purpose of a feature store and identify best practices.
- Explore training pipeline functions and identify the best practices for managing a training pipeline.
- Discuss the benefits of model versioning.
- Describe what a model registry is and identify model registry contents.