From Siri to Netflix, SMS to Google, the world wouldn’t be what it is today without Natural Language Processing (NLP) and Large Language Models (LLMs).

Be part of the AI revolution with this three-week course from PragmaticAI. Enhance your technical expertise in language models while gaining hands-on experience in deploying and fine-tuning advanced AI solutions.

You’ll work with cutting-edge open-source programs and platforms, equipping yourself with a unique skill set that will help you stand out in the competitive AI job market.

Harness cutting-edge tech tools

You’ll begin this course with an introduction to LLMs and how they work, exploring their benefits and risks, and understanding how foundation models serve as the backbone for a wide range of AI applications.

You’ll work with popular open-source NLP tools and projects, such as Llama and Whisper.cpp, and learn how to access other pre-trained models from repository platforms, like HuggingFace and Transformers.

Enhance production workflows and LLM performance

Next, you’ll explore best practices for deploying LLMs, focusing on serverless inference and efficient, Rust-based implementations that enable faster, scalable AI operations.

You’ll leverage tools like Skypilot, Lorax, and Ludwig, which streamline model fine-tuning and deployment in production environments.

Master RAG and navigate ethical challenges in Generative AI

You’ll also delve into Retrieval Augmented Generation (RAG), a powerful method for improving model performance, and learn to manage data for RAG applications and optimise LLM outputs.

With tools like Glaze, you’ll gain a deeper understanding of responsible AI deployment in real-world applications, as well as learn to navigate the ethical and regulatory challenges of Generative AI.