<LLM: Learning by Building from Scratch> Commentary Lecture
This course covers the GitHub notebooks and bonus content for <Building an LLM from Scratch> (Gilbut, 2025). GitHub: https://github.com/rickiepark/llm-from-scratch/ <Building an LLM from Scratch> is the Korean translation of the bestseller <Build a Large Langauge Model (from Scratch)> (Manning, 2024) written by Sebastian Raschka. Starting from scratch and building a complete version of OpenAI’s GPT-2 model, this book provides a way to learn how large language models work and how to use them.
581 learners
Level Basic
Course period Unlimited
"LLM & AI with PyTorch" Book Publication and Event Announcement
Hello. I'm Haesun Park.
It's been a while, but I'm happy to announce the publication of a new book.
<AI and Machine Learning for Coders> author Laurence Moroney's new book <Llama 2 and Beyond: A Guide to LLMs with PyTorch> has been published!

The previous book focused on deep learning applications using the TensorFlow ecosystem. This book uses PyTorch instead of TensorFlow and focuses on generative AI, such as LLMs and diffusion models. It is now available at online and offline bookstores! The e-book has also been released! 🙂
Now available at online bookstores. [Kyobo Book Centre] [Yes24] [Aladin] [Hanbit Media]
504 pages,
36,000won –> 32,400 won, E-book: 25,920 won
I have created a short video summarizing what's new compared to the previous edition. Share this video on your social media, and five winners will be selected to receive a copy of from Hanbit Media! You must register on the Google Form after sharing it on social media. Please refer to the instructions below!
Video URL to share: https://youtu.be/vEwY31kDtl4
Please register the SNS URL where your shared content can be viewed in the Google Form (https://forms.gle/9CMP37YMugpkA8G96).
If you cannot register the URL address, please upload a screenshot instead.
Event Period: 3/5 (Thu) ~ 3/13 (Fri)
Winner Announcement: 3/16 (Mon) (Winners will be contacted individually)
The books will be sent directly by Hanbit Media.
We look forward to your participation.
Thank you!




