inflearn logo
강의

Course

Instructor
inflearn logo
Challenge
Ended
AI Technology

/

Deep Learning & Machine Learning

<Build Your Own LLM from Scratch> Completion Challenge

This challenge is a 7-week program to read through the book <Build a Large Language Model (From Scratch)> (Gilbut, 2025) together with the translator. If you have any questions about the challenge or the book, please feel free to contact us anytime via Inflearn, the translator's blog (https://tensorflow.blog/llm-from-scratch/), or the KakaoTalk open chat room (http://bit.ly/tensor-chat, participation code: flow).

PyTorch
gpt-2
self-attention
LLM
book-challenge

53개 수업 학습

8회 미션 수행

무제한 복습, 내 것으로 만들어요.

질문하고 즉시 답을 얻어요.

성취의 증표, 수료증을 발급해요.

haesunpark님과 함께해요!

22,945

Learners

403

Reviews

131

Answers

4.9

Rating

11

Courses

I majored in mechanical engineering, but since graduation, I have been consistently reading and writing code. I am a Google AI/Cloud GDE and a Microsoft AI MVP. I run the TensorFlow blog (tensorflow.blog) and enjoy exploring the boundary between software and science by writing and translating books on machine learning and deep learning.

ml-dl-roadmap.png.webp

 He has authored "Deep Learning by Building Alone" (Hanbit Media, 2025), "Machine Learning + Deep Learning Alone (Revised Edition)" (Hanbit Media, 2025), "Data Analysis with Python Alone" (Hanbit Media, 2023), "The Art of Conversing with ChatGPT" (Hanbit Media, 2023), and "Do it! Introduction to Deep Learning" (EasysPublishing, 2019).

He has translated dozens of books into Korean, including "LLM Fine-Tuning: Quick Core Concepts!" (Insight, 2026), "Learning LLM & AI with PyTorch" (Hanbit Media, 2026), "Large Language Models: Quick Core Concepts!" (Insight, 2025), "Machine Learning: Quick Core Concepts!" (Insight, 2025), "Learning LLM by Building from Scratch" (Gilbut, 2025), "Hands-On LLM" (Hanbit Media, 2025), "Machine Learning Q & AI" (Gilbut, 2025), "Mathematics for Developers" (Hanbit Media, 2024), "Practical ML Problem Solving with Python" (Hanbit Media, 2024), "Machine Learning Textbook: PyTorch Edition" (Gilbut, 2023), "Stephen Wolfram's ChatGPT Lecture" (Hanbit Media, 2023), "Hands-On Machine Learning, 3rd Edition" (Hanbit Media, 2023), "Generative Deep Learning, 2nd Edition" (Hanbit Media, 2023), "Python for Awakening the Coding Brain" (Hanbit Media, 2023), "Natural Language Processing with Transformers" (Hanbit Media, 2022), "Deep Learning with Python, 2nd Edition" (Gilbut, 2022), "Machine Learning & Deep Learning for Developers" (Hanbit Media, 2022), "Gradient Boosting with XGBoost and Scikit-Learn" (Hanbit Media, 2022), "Deep Learning with TensorFlow.js" (Gilbut, 2022), and "Introduction to Machine Learning with Python, 2nd Edition" (Hanbit Media, 2022).

More

Challenge Information

The recruitment period for this challenge is from September 23rd to October 5th.

The challenge schedule will run for 8 weeks, from October 6th to November 30th.

(The actual challenge curriculum is 7 weeks, but the period has been set to 8 weeks to account for the Chuseok holiday)


If you participate in the challenge, the following information and benefits will be provided.

  1. The translator provides video lectures explaining the text.

  2. Weekly reading verification and progress tracking

  3. Free coupons for a paid lecture (valued at 60,000 KRW) explaining the book's code will be provided to all challenge participants.

    1. <Building LLMs from Scratch> Code Explanation Lecture (Free coupons will be issued in bulk on October 6th)

  4. Upon completion of the challenge, 20,000 points that can be used like cash on the Gilbut website will be awarded (Special thanks to Gilbut Publishing for sponsoring the points)

Reference Sites

Book Introduction

Follow the code line by line, and your very own GPT will be complete!
A practical guide to mastering the principles of LLMs by implementing GPT from scratch.

Complex concepts are explained through illustrations, and LLMs are learned by building them yourself. This book is a practical introductory guide to LLMs that allows you to learn the structure and operating principles of large language models by implementing them from scratch. Rather than just explaining concepts, it starts with text preprocessing, tokenization, and embedding processes, and step-by-step builds self-attention, multi-head attention, and Transformer blocks. It then integrates these components to complete an actual GPT model, directly handling key elements of modern architecture design such as parameter counts, training stabilization techniques, activation functions, and normalization methods. Furthermore, it provides in-depth guidance on the pre-training and fine-tuning processes. You can practice pre-training on unlabeled data, tuning the model for downstream tasks like text classification, and even instruction-based learning techniques that are currently in the spotlight. It also covers the latest topics, such as LoRA-based Parameter-Efficient Fine-Tuning (PEFT), offering a broad range of methods to connect LLMs to real-world services and research. All concepts are implemented in PyTorch code and optimized for practice even in standard laptop environments. By following the implementation process in this book, you will naturally understand what happens inside an LLM and gain a hands-on grasp of how large language model mechanisms work.

i9791140715848

10월

5일

챌린지 시작일

2025년 10월 5일 PM 03:00

챌린지 종료일

2025년 11월 30일 PM 02:59

챌린지 커리큘럼

All

61 lectures ∙ (4hr 38min)

Course Materials:

챌린지에서 배워요

  • Implement a complete LLM from scratch directly in code.

  • You will learn the core components that make up LLMs, including Transformers and Attention.

  • Learn how to pre-train an LLM similar to GPT.

  • Learn how to fine-tune an LLM for classification.

  • Learn how to fine-tune an LLM to follow human instructions and respond.

Recommended for
these people

Who is this course right for?

  • Those who want to understand the operating principles of Large Language Models (LLMs) in detail

  • Those who want to pre-train and fine-tune LLMs using PyTorch and the transformers package

  • Those who want to know the architecture of OpenAI's GPT-2 model

  • Someone who isn't satisfied unless they make everything themselves!

Need to know before starting?

  • Basic knowledge of Python programming is required.

  • If you are not familiar with PyTorch, please refer to Appendix A at the back of the book.

Reviews

All

90 reviews

5.0

90 reviews

  • devpaw님의 프로필 이미지
    devpaw

    Reviews 3

    ∙

    Average Rating 5.0

    5

    74% enrolled

    I've never had this much fun studying LLM - both the book and the lectures were great

    • haesunpark
      Instructor

      Thank you!

  • myhkjung5761님의 프로필 이미지
    myhkjung5761

    Reviews 5

    ∙

    Average Rating 5.0

    5

    100% enrolled

    Thank you for translating and introducing such great materials, and for preparing the lectures and challenges!

    • haesunpark
      Instructor

      I hope this helps! 😊

  • calculator님의 프로필 이미지
    calculator

    Reviews 144

    ∙

    Average Rating 4.8

    5

    100% enrolled

    My first book completion challenge... It helped me understand how LLMs work. And I'm happy that I succeeded in the challenge too 😊😊 I'm glad I participated.

    • haesunpark
      Instructor

      Congratulations on completing it! :)

  • amgwon4343님의 프로필 이미지
    amgwon4343

    Reviews 4

    ∙

    Average Rating 5.0

    5

    33% enrolled

    It's great for motivation to be able to study together through the challenge, and it feels like I'm studying with focus for the first time in a while. I'll learn well with this good lecture.

    • haesunpark
      Instructor

      Keep fighting until the end. Thank you!

  • elliraum님의 프로필 이미지
    elliraum

    Reviews 4

    ∙

    Average Rating 5.0

    5

    100% enrolled

    Thanks to you, I was able to study. Thank you for providing such a great book and opening the challenge! I'll work even harder on my reviews!!

    • haesunpark
      Instructor

      Thank you. Fighting!

FAQs

취소 및 환불 규정
챌린지는 지식공유자가 설정한 수업 최소 정원이 충족되지 않을 경우, 폐강 안내가 고지되며 결제 내역이 자동취소됩니다.

haesunpark's other courses

Check out other courses by the instructor!

<From Scratch: Building and Learning LLMs> Commentary LectureCourse Thumbnail

<From Scratch: Building and Learning LLMs> Commentary Lecture

haesunpark

$77.00

Basic / PyTorch, gpt-2, transformer, LLM, Fine-Tuning

4.8

(23)

500+

This is a course covering the GitHub notebooks and bonus content from <Build a Large Language Model from Scratch> (Gilbut, 2025). GitHub: https://github.com/rickiepark/llm-from-scratch/ <Build a Large Language Model from Scratch> is the Korean translation of the bestseller <Build a Large Language Model (from Scratch)> (Manning, 2024) by Sebastian Raschka. This book provides a way to learn and utilize the operating principles of large language models by building a complete model starting from scratch with OpenAI's GPT-2 model.

Basic

Basic

PyTorch, gpt-2, transformer

<From Scratch: Building and Learning LLMs> Commentary LectureCourse Thumbnail

<From Scratch: Building and Learning LLMs> Commentary Lecture

haesunpark

$77.00

Basic / PyTorch, gpt-2, transformer, LLM, Fine-Tuning

4.8

(23)

500+
Self-study machine learning + deep learningCourse Thumbnail

Self-study machine learning + deep learning

haesunpark

Free

Basic / Machine Learning(ML), Deep Learning(DL)

4.9

(97)

8,800+

The ultimate machine learning and deep learning tutorial that teaches you like a 1:1 private lesson with Hanbit Media's Honkong series, understand with hundreds of hand drawings, and practice right away with just a browser through Google Colab

Basic

Basic

Machine Learning(ML), Deep Learning(DL)

Self-study machine learning + deep learningCourse Thumbnail

Self-study machine learning + deep learning

haesunpark

Free

Basic / Machine Learning(ML), Deep Learning(DL)

4.9

(97)

8,800+
Do It! Introduction to Deep LearningCourse Thumbnail

Do It! Introduction to Deep Learning

haesunpark

Free

Basic / Deep Learning(DL), Machine Learning(ML), Artificial Neural Network

4.9

(74)

4,800+

This lecture guides readers to deep learning with the most appropriate pace and straight direction, one step from concept to formula and one step from coding. In addition, there are over 100 graphs, illustrations, and diagrams, so you can easily and quickly accept abstract concepts. Another unique feature of this lecture is that you can start practicing right away by simply accessing a web browser without installing a program. After comfortably understanding the theory, you can directly code and conquer four representative deep learning problems with your eyes, so it is not lacking as a textbook for deep learning. The concepts or terms that you must go over are reviewed twice in the ‘Wait! Let’s move on to the next’ corner in the middle of the text and the ‘Memory Card’ corner at the end of the chapter to increase the learning effect. Let’s quickly overcome deep learning head-on with ‘Do it! Introduction to Deep Learning.’

Basic

Basic

Deep Learning(DL), Machine Learning(ML), Artificial Neural Network

Do It! Introduction to Deep LearningCourse Thumbnail

Do It! Introduction to Deep Learning

haesunpark

Free

Basic / Deep Learning(DL), Machine Learning(ML), Artificial Neural Network

4.9

(74)

4,800+
Hands-On Machine Learning 2Course Thumbnail

Hands-On Machine Learning 2

haesunpark

Free

Basic / Tensorflow, Machine Learning(ML), Deep Learning(DL), Keras, Reinforcement Learning(RL), NLP, Scikit-Learn

4.7

(56)

6,600+

This course covers the content of the Amazon bestseller <Hands-On Machine Learning, 2nd Edition>. You will learn various machine learning algorithms and evaluation methods using Scikit-Learn, a representative machine learning library. Additionally, you will build a foundation in both theory and practice, ranging from artificial neural networks to reinforcement learning, using the most famous deep learning libraries, TensorFlow and Keras. This course is not yet complete. One to two lectures will be added every week.

Basic

Basic

Tensorflow, Machine Learning(ML), Deep Learning(DL)

Hands-On Machine Learning 2Course Thumbnail

Hands-On Machine Learning 2

haesunpark

Free

Basic / Tensorflow, Machine Learning(ML), Deep Learning(DL), Keras, Reinforcement Learning(RL), NLP, Scikit-Learn

4.7

(56)

6,600+
Large Language Models, Just the Essentials!Course Thumbnail

Large Language Models, Just the Essentials!

haesunpark

$34.10

Beginner / Artificial Neural Network, PyTorch, LLM, Fine-Tuning, RNN

4.7

(10)

100+

This is a lecture covering LLM theory and practical examples based on <Large Language Models, Just the Essentials!> (Insight, 2025).

Beginner

Beginner

Artificial Neural Network, PyTorch, LLM

Large Language Models, Just the Essentials!Course Thumbnail

Large Language Models, Just the Essentials!

haesunpark

$34.10

Beginner / Artificial Neural Network, PyTorch, LLM, Fine-Tuning, RNN

4.7

(10)

100+
Machine Learning, Just the Essentials, Fast!Course Thumbnail

Machine Learning, Just the Essentials, Fast!

haesunpark

$34.10

Beginner / Artificial Neural Network, CNN, linear-regression, RNN, ensembles

4.8

(8)

100+

This is a lecture covering machine learning theory and practical examples based on <Machine Learning, Just the Essentials!> (Insight, 2025).

Beginner

Beginner

Artificial Neural Network, CNN, linear-regression

Machine Learning, Just the Essentials, Fast!Course Thumbnail

Machine Learning, Just the Essentials, Fast!

haesunpark

$34.10

Beginner / Artificial Neural Network, CNN, linear-regression, RNN, ensembles

4.8

(8)

100+
Python for Waking Up Your Coding BrainCourse Thumbnail

Python for Waking Up Your Coding Brain

haesunpark

Free

Beginner / Python, Pandas

4.8

(12)

900+

Wake up your sleeping coding brain. From Python basics to machine learning, all in one book! Based on MIT lectures, this computer science introductory book is accessible even for beginners with no prior knowledge of programming. Wake up your dormant coding brain with essential introductory topics such as computational thinking and simple algorithms. Through the "Finger Exercise" problems provided in each chapter, you will explore practical subjects like data visualization, simulation, data calculation techniques, and machine learning.

Beginner

Beginner

Python, Pandas

Python for Waking Up Your Coding BrainCourse Thumbnail

Python for Waking Up Your Coding Brain

haesunpark

Free

Beginner / Python, Pandas

4.8

(12)

900+

$17.60