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

7h 12m 10s
English
Paid

Course description

Master an in-demand skill that companies are looking for: developing and implementing custom LLMs. In this course, you will learn how to fine-tune open large language models on closed/corporate data and deploy your models using AWS (SageMaker, Lambda, API Gateway) and Streamlit to provide a convenient interface for employees and clients.

This is not "just another introductory AI course." It is a practical deep dive into the skills that set AI engineers apart on real projects. You will perform fine-tuning using QLoRA, a method that drastically reduces resource consumption, and then turn the model into a production service.

Read more about the course

What you will master:

  1. Fine-tuning open-source LLM on your own datasets (including corporate ones).
  2. Practice with QLoRA, bfloat16 training, chunking datasets, attention masks.
  3. The Hugging Face ecosystem (including Estimator API) and MLOps pipeline on AWS.
  4. Model deployment and integration: SageMaker endpoints, Lambda, API Gateway, monitoring.
  5. Creating a simple business UI on Streamlit.


Outcome: from theory to code and production - the complete development cycle of applied AI for business cases.

Who it benefits and what roles it prepares for:

  1. AI Engineer / ML Engineer - designing, fine-tuning, and producing models.
  2. AI Specialist - creating applied solutions based on AI.
  3. Data Scientist - data preparation, EDA, and building models for company tasks.
  4. AI Research Scientist - in-depth work with attention mechanisms and LLM.
  5. Cloud Engineer - architecture and best deployment practices in AWS.
  6. DevOps Engineer - automation, release, and monitoring of ML services (CloudWatch, etc.).
  7. Software Engineer - integrating models into applications with scalability in mind.
  8. Data Engineer - data pipelines, storage (S3), preprocessing.
  9. Technical Product Manager - planning and releasing ML products, metrics, and monitoring.


If you want to catch the "AI wave," customizing LLM for business tasks is a great entry point and growth opportunity.

Watch Online

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

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

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

Comments

0 comments

Want to join the conversation?

Sign in to comment

Similar courses

Create your Dream Apps with Cursor and Claude AI

Create your Dream Apps with Cursor and Claude AI

Sources: designcode.io
In this course, you will learn to create dream web applications from scratch using Cursor, Claude AI, and a set of powerful AI tools. You will master...
5 hours 46 minutes 6 seconds
Full-Stack SaaS Development Course on Cloudflare Workers

Full-Stack SaaS Development Course on Cloudflare Workers

Sources: backpine labs
This is a practical training where you will step by step master full-stack development of SaaS applications based on Cloudflare Workers. The program is built...
11 hours 27 minutes 15 seconds
Amazon EKS Starter: Docker on AWS EKS with Kubernetes

Amazon EKS Starter: Docker on AWS EKS with Kubernetes

Sources: udemy
Setting up and maintaining Kubernetes yourself on any cloud provider is painful... but now with Amazon EKS, the management of the Kubernetes control
5 hours 30 minutes 7 seconds
Local LLMs via Ollama & LM Studio - The Practical Guide

Local LLMs via Ollama & LM Studio - The Practical Guide

Sources: Academind Pro
AI assistants like ChatGPT and Google Gemini have become everyday tools. However, when privacy, cost, offline functionality, or flexible...
3 hours 52 minutes 28 seconds