EdX

Beginning Llamafile (edX)

Offered by AI (Pragmatic AI Labs),
Beginning Llamafile (edX)

Learn to serve powerful language models as practical, scalable web APIs using the llama.cpp server. Keep your data private and avoid cloud latency and fees.

Class Deals by MOOC List - Click here and see EdX's Active Discounts, Deals, and Promo Codes.

In this course, you will:

  • Gain the skills to expose large language models through REST API endpoints
  • Learn how to configure the llama.cpp server to customize model behavior
  • Understand how to efficiently handle requests and integrate language model capabilities into applications
  • Reinforce concepts through hands-on exercises and code examples using tools like curl and Python
  • Be equipped to deploy robust language model APIs for various NLP tasks

The course empowers you to harness state-of-the-art NLP models in your projects through a convenient and performant API interface, focusing on the practical aspects of serving large language models in production environments using the efficient and flexible llama.cpp framework.
This course is part of the Generative AI Fundamentals Professional Certificate.

What you'll learn

  • Installing and using the Cosmopolitan Libc toolkit
  • Running language models locally with llamafile
  • Understanding the Mixtral model license and llamafile packaging
  • Developing portable command-line interfaces with Cosmopolitan
  • Interacting with the llamafile API for NLP tasks

Syllabus

Module 1: Getting Started with Mozilla Llamafile (2 hours)

  • Video: Meet your instructor: Alfredo Deza (1 minute) [Preview module]
  • Reading: Meet your instructor: Noah Gift (1 minute)
  • Reading: Connect with your instructors (1 minute)
  • Reading: Course structure and etiquette (1 minute)
  • Reading: Key Terms (5 minutes)
  • Reading: What is Llamafile? (5 minutes)
  • Video: Llamafile overview by Mozilla (5 minutes)
  • Video: Using the Llamafile API (2 minutes)
  • Video: Creating a Llamafile (5 minutes)
  • Reading: Cosmopolitan (5 minutes)
  • Video: Building portable binaries with Cosmopolitan (4 minutes)
  • Video: Building a phrase generator with cosmopolitan (3 minutes)
  • Reading: Lesson Reflection (5 minutes)
  • Assignment: Quiz-Key Components of Llamafile (10 minutes)
  • Reading: Key Terms (1 minute)
  • Reading: Bash Phrase Generator (5 minutes)
  • Ungraded Lab: Cosmopolitan (10 minutes)
  • Reading: Lesson Reflection (5 minutes)
  • Assignment: Quiz-Portable CLI with Cosmopolitan (10 minutes)
  • Reading: Key Terms (5 minutes)
  • Reading: What are LLMs? (5 minutes)
  • Video: Getting Started with Llamafile (3 minutes)
  • Video: Llamafile local system metrics (3 minutes)
  • Ungraded Lab: Portable CLI (10 minutes)
  • Reading: Lesson Reflection (5 minutes)
  • Assignment: Quiz-Running Llamafile (10 minutes)
  • Reading: Key Terms (1 minute)
  • Reading: Llamafile server (5 minutes)
  • Ungraded Lab: Local Llamafile API (10 minutes)
  • Reading: Course Conclusion (5 minutes)
  • Reading: Next Steps (1 minute)
  • Assignment: Final Quiz-Llamafile (10 minutes)
  • Discussion Prompt: Meet and Greet (optional) (1 minute)
Go to Class
MOOC List is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Related Courses

Computer Graphics (edX) EdX
University of California, San Diego,UC San DiegoX

Computer Graphics (edX)

CS: Software Engineering Computer Science

Learn to create images of 3D scenes in both real-time and with realistic raytracing in this introductory computer graphics course. Today, computer graphics is a central part of our lives, in movies, games, computer-aided design, virtual simulators, visualization and even imaging products and cameras.

Self Paced
Self-Paced
OpenGL GLSL 3D Graphics
Details
Introducción a la programación en C: Tipos de datos y estructuras (edX) EdX
Universidad Autonoma de Madrid

Introducción a la programación en C: Tipos de datos y estructuras (edX)

Engineering Computer Science

Aprende a programar en C, uno de los lenguajes de programación más usados. En este curso en línea adquirirás los conocimientos necesarios para comenzar a convertirte en un experto en C. Este curso en línea te permitirá aprender los conceptos básicos que te ayudarán a desarrollar las habilidades de programación necesarias para iniciarte en el lenguaje C.

Self Paced
Self-Paced
Programming Structures C Language
Details
Dynamic Programming: Applications In Machine Learning and Genomics (edX) EdX
University of California, San Diego,UC San DiegoX

Dynamic Programming: Applications In Machine Learning and Genomics (edX)

Sci: Biology & Life Sciences Sci: Mathematics

Learn how dynamic programming and Hidden Markov Models can be used to compare genetic strings and uncover evolution. If you look at two genes that serve the same purpose in two different species, how can you rigorously compare these genes in order to see how they have evolved away from each other?

Self Paced
Self-Paced
Machine Learning Genomics Dynamic Programming
Details
Introduction to Cloud Computing (edX) EdX
IBM

Introduction to Cloud Computing (edX)

Security & Networking

Master the core concepts in Cloud Computing, from service and deployment models, to cloud architecture, security, new technologies, and possible careers. This course introduces you to the core concepts of cloud computing. You will gain the foundational knowledge required for understanding cloud computing from both business and practitioner perspectives.

Self Paced
Self-Paced
Security SaaS Cloud Computing
Details
Big Data Capstone Project (edX) EdX
University of Adelaide,AdelaideX

Big Data Capstone Project (edX)

Statistics & Data Analysis Data Science

Further develop your knowledge of big data by applying the skills you have learned to a real-world data science project. This project will give you the opportunity to deepen your learning by giving you valuable experience in evaluating, selecting and applying relevant data science techniques, principles and theory to a data science problem. This project will see you plan and execute a reasonably substantial project and demonstrate autonomy, initiative and accountability.

Self Paced
Self-Paced
Big Data Data Science Data Analytics
Details