CF

AI Engineering: Customizing LLMs for Business (Fine-Tuning LLMs with QLoRA & AWS)

7h 12m 10s
English
Paid

AI Engineering: Customizing LLMs for Business (Fine-Tuning LLMs with QLoRA & AWS) is a 58-lesson 7 hours 12 minutes self-paced course by Zero To Mastery. Plenty of courses cover generative AI at a surface level.

Course facts

Lessons
58
Duration
7 hours 12 minutes
Level
All levels
Language
English
Updated
Instructor
Zero To Mastery
Price
Premium

Plenty of courses cover generative AI at a surface level. This one, from Zero To Mastery, goes into the part that actually distinguishes an AI engineer on a real project: fine-tuning an open-source LLM on your own data and getting it into production.

Fine-Tuning

You'll fine-tune open LLMs using QLoRA, a resource-efficient approach, working hands-on with bfloat16 training, dataset chunking, and attention masks through the Hugging Face ecosystem, including its Estimator API.

Getting to Production

From there, the 58-lesson course covers building an MLOps pipeline on AWS and deploying the model through SageMaker endpoints, Lambda, and API Gateway, complete with monitoring, plus building a simple Streamlit interface so employees or clients can actually use it.

Who It's For

The material is built around real career paths: AI/ML engineers, AI specialists, data scientists, cloud and DevOps engineers, software engineers integrating models into apps, data engineers, and technical product managers planning AI releases.

Additional

https://github.com/patrikszepesi/qlora-course

Who teaches AI Engineering: Customizing LLMs for Business (Fine-Tuning LLMs with QLoRA & AWS)? Zero To Mastery

Zero To Mastery thumbnail

Zero To Mastery (ZTM) is a Toronto-based online coding academy founded by Andrei Neagoie, originally a senior developer at large Canadian tech firms before turning to teaching full-time. The academy's signature is the cohort-based bootcamp track combined with a deep self-paced course library, all aimed at career-changers and self-taught developers preparing to land software-engineering roles at top companies.

The instructor roster has grown well beyond Andrei to include other senior practitioners: Daniel Bourke (machine learning), Aleksa Tešić (DevOps), Jacinto Wong, and others. Courses cover the full software-engineering career path: web development with React and Next.js, Python, machine learning and deep learning, DevOps and cloud, system design, mobile, and the algorithm / data-structure interview prep that gates engineering jobs.

The CourseFlix listing under this source carries over 120 ZTM courses spanning that full range. Material is paid; ZTM itself runs on a monthly / annual membership model. The teaching style favours long-form, project-based courses where students build complete portfolio-quality applications rather than disconnected feature tutorials.

What lessons are included in AI Engineering: Customizing LLMs for Business (Fine-Tuning LLMs with QLoRA & AWS)?

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 58 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Course Introduction (What We're Building)
All Course Lessons (58)
#Lesson TitleDurationAccess
1
Course Introduction (What We're Building) Demo
05:20
2
Signing in to AWS
04:31
3
Creating an IAM User
05:30
4
Using our new IAM User
03:13
5
What To Do In Case You Get Hacked!
01:31
6
Creating a SageMaker Domain
02:29
7
Logging in to our SageMaker Environment
04:54
8
Introduction to JupyterLab
07:38
9
Sagemaker Sessions, Regions, and IAM Roles
07:51
10
Examining Our Dataset from HuggingFace
13:30
11
Tokenization and Word Embeddings
09:09
12
HuggingFace Authentication with Sagemaker
04:22
13
Applying the Templating Function to our Dataset
08:44
14
Attention Masks and Padding
15:56
15
Star Unpacking with Python
04:04
16
Chain Iterator, List Constructor and Attention Mask example with Python
10:23
17
Understanding Batching
08:12
18
Slicing and Chunking our Dataset
07:32
19
Creating our Custom Chunking Function
16:07
20
Tokenizing our Dataset
09:31
21
Running our Chunking Function
04:31
22
Understanding the Entire Chunking Process
08:33
23
Uploading the Training Data to AWS S3
05:54
24
Setting Up Hyperparameters for the Training Job
06:48
25
Creating our HuggingFace Estimator in Sagemaker
06:46
26
Introduction to Low-rank adaptation (LoRA)
08:12
27
LoRA Numerical Example
10:56
28
LoRA Summarization and Cost Saving Calculation
09:09
29
(Optional) Matrix Multiplication Refresher
04:46
30
Understanding LoRA Programatically Part 1
12:33
31
Understanding LoRA Programatically Part 2
05:49
32
Bfloat16 vs Float32
08:11
33
Comparing Bfloat16 Vs Float32 Programatically
06:33
34
Setting up Imports and Libraries for the Train Script
07:20
35
Argument Parsing Function Part 1
07:57
36
Argument Parsing Function Part 2
10:55
37
Understanding Trainable Parameters Caveats
14:31
38
Introduction to Quantization
07:36
39
Identifying Trainable Layers for LoRA
07:20
40
Setting up Parameter Efficient Fine Tuning
04:36
41
Implement LoRA Configuration and Mixed Precision Training
10:35
42
Understanding Double Quantization
04:22
43
Creating the Training Function Part 1
14:15
44
Creating the Training Function Part 2
07:17
45
Exercise: Imposter Syndrome
02:57
46
Finishing our Sagemaker Script
05:09
47
Gaining Access to Powerful GPUs with AWS Quotas
05:11
48
Final Fixes Before Training
03:55
49
Starting our Training Job
07:16
50
Inspecting the Results of our Training Job and Monitoring with Cloudwatch
11:24
51
Deploying our LLM to a Sagemaker Endpoint
17:58
52
Testing our LLM in Sagemaker Locally
08:19
53
Creating the Lambda Function to Invoke our Endpoint
08:56
54
Creating API Gateway to Deploy the Model Through the Internet
02:37
55
Implementing our Streamlit App
05:12
56
Streamlit App Correction
03:27
57
Congratulations and Cleaning up AWS Resources
02:39
58
Thank You!
01:18
Unlock unlimited learning

Get instant access to all 57 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

What courses are similar to AI Engineering: Customizing LLMs for Business (Fine-Tuning LLMs with QLoRA & AWS)?

More courses by Zero To Mastery

Frequently asked questions

What prerequisites are needed before enrolling in this course?
The course assumes familiarity with basic programming concepts and general AI principles. A background in Python is beneficial, as the course involves significant coding, particularly in sections dealing with JupyterLab and Python functions. Additionally, understanding of cloud services, particularly AWS, is useful, as the course covers creating IAM users and deploying models using AWS tools like SageMaker.
What practical projects will I work on during the course?
The course involves several hands-on projects, such as fine-tuning open-source Large Language Models (LLMs) with your own datasets, including corporate data, and deploying these models using AWS tools like SageMaker, Lambda, and API Gateway. You'll also build a simple business interface with Streamlit, which allows for interaction with the deployed models.
Who is the target audience for this course?
This course is designed for professionals aiming to become AI Engineers, Machine Learning Engineers, or Data Scientists. It's particularly suited for those who want to specialize in developing and deploying large language models in business contexts, leveraging AWS infrastructure and tools like Hugging Face.
How does this course compare to other AI courses in terms of depth and scope?
Unlike introductory AI courses, this course provides a practical, in-depth exploration of fine-tuning and deploying LLMs using advanced techniques like QLoRA and bfloat16 training. The course covers the complete development cycle from dataset preparation to deployment, emphasizing real-world application and efficiency, such as resource-saving techniques in model fine-tuning.
Is there a focus on any specific tools or platforms?
Yes, the course focuses heavily on the AWS ecosystem for model deployment, including tools like SageMaker, Lambda, and API Gateway. It also extensively uses the Hugging Face platform for managing datasets and model training, and Streamlit for creating user interfaces.
What topics are not covered in this course?
The course does not cover foundational AI concepts or introductory programming skills. It assumes these are already understood. Additionally, it does not delve into the theoretical underpinnings of machine learning algorithms or detailed mathematical derivations, focusing instead on practical implementation and deployment of LLMs.
What is the expected time commitment for this course?
The course consists of 58 lessons, which are designed to be comprehensive and detailed. While the exact time commitment may vary depending on your prior experience, you should expect to dedicate a significant amount of time to both the lessons and the hands-on projects to fully grasp the course content and outcomes.