DeepLearning.AI

Pretraining LLMs

Lucy Park
Sung Kim

Instructors: Lucy Park

Gain insight into a topic and learn the fundamentals.
Beginner level

Recommended experience

1 hour to complete
Flexible schedule
Learn at your own pace
Gain insight into a topic and learn the fundamentals.
Beginner level

Recommended experience

1 hour to complete
Flexible schedule
Learn at your own pace

What you'll learn

  • Gain in-depth knowledge of pretraining an LLM, covering data preparation, model configuration, and performance assessment.

  • Explore model architecture options, including modifying Meta’s Llama models for various sizes and initializing weights randomly or from other models.

  • Learn innovative pretraining techniques like Depth Upscaling, which can reduce training costs by up to 70%.

Skills you'll gain

Details to know

Recently updated!

July 2024

Assessments

1 assignment

Taught in English

See how employees at top companies are mastering in-demand skills

Placeholder

There is 1 module in this course

In Pretraining LLMs you’ll explore the first step of training large language models using a technique called pretraining. You’ll learn the essential steps to pretrain an LLM, understand the associated costs, and discover how starting with smaller, existing open source models can be more cost-effective.Pretraining involves teaching an LLM to predict the next token using vast text datasets, resulting in a base model, and this base model requires further fine-tuning for optimal performance and safety. In this course, you’ll learn to pretrain a model from scratch and also to take a model that’s already been pretrained and continue the pretraining process on your own data. In detail: 1. Explore scenarios where pretraining is the optimal choice for model performance. Compare text generation across different versions of the same model to understand the performance differences between base, fine-tuned, and specialized pre-trained models. 2. Learn how to create a high-quality training dataset using web text and existing datasets, which is crucial for effective model pretraining. 3. Prepare your cleaned dataset for training. Learn how to package your training data for use with the Hugging Face library. 4. Explore ways to configure and initialize a model for training and see how these choices impact the speed of pretraining. 5. Learn how to configure and execute a training run, enabling you to train your own model. 6. Learn how to assess your trained model’s performance and explore common evaluation strategies for LLMs, including important benchmark tasks used to compare different models’ performance. After taking this course, you’ll be equipped with the skills to pretrain a model—from data preparation and model configuration to performance evaluation.

What's included

1 assignment1 app item

Instructors

Lucy Park
DeepLearning.AI
1 Course562 learners

Offered by

DeepLearning.AI

Recommended if you're interested in Software Development

Why people choose Coursera for their career

Felipe M.
Learner since 2018
"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."
Jennifer J.
Learner since 2020
"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."
Larry W.
Learner since 2021
"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."
Chaitanya A.
"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

New to Software Development? Start here.

Placeholder

Open new doors with Coursera Plus

Unlimited access to 7,000+ world-class courses, hands-on projects, and job-ready certificate programs - all included in your subscription

Advance your career with an online degree

Earn a degree from world-class universities - 100% online

Join over 3,400 global companies that choose Coursera for Business

Upskill your employees to excel in the digital economy

Frequently asked questions