Skip to main content
Other Professional Courses2025-7 Edition100% Free Video Course

Manning – Master and Build Large Language Models

Master and Build Large Language Models. This course helps participants become a professional modeler by learning the concepts and building a large language model. This course teaches the best way to understand large language models (LLMs) by building them. Led by experienced AI researcher Sebastian Raschka, participants will learn the inner workings of these models. In this course, you will learn how to code all the parts of an LLM, prepare a suitable dataset, fine-tune the model for text classification, use human feedback, and load pre-trained weights. This course is designed for software engineers, data scientists, and machine learning researchers who plan to build or adapt LLMs. It also includes six prerequisite videos by AI expert Abhinav Kimothy that cover Python basics, vector mathematics, PyTorch essentials, neural networks, and deep learning building blocks. These videos cover setting up a Python environment, mastering basic concepts, understanding the mathematics of AI, learning PyTorch operations, and the basics of neural networks. This comprehensive course ensures that participants, regardless of their initial knowledge level, will succeed in building large language models.

5.0
(2 reviews)
22.6 Hours On-Demand
Created by Sebastian Raschka
Uploaded Sep 2026
English
Beginner to advanced
Manning – Master and Build Large Language Models
Preview This Course
Free$129.99100% Free

Instant high-definition streaming with zero paywalls.

Course Features:
22.6 hours on-demand video
54 complete lectures
1 downloadable project zip file(s)
Streamable on mobile, tablet & desktop
Self-paced curriculum with progress tracking
Direct MP4 downloads & offline video access
Verified course archives hosted on cloud infrastructure.

What You'll Master in this Course

Planning and coding all parts of an LLM.
Preparing a suitable dataset for LLM training.
Fine-tune LLMs for text classification with your own data.
Using human feedback to ensure LLM follows instructions.
Loading pre-trained weights into an LLM

Course Curriculum54 Lectures

1 sections • 22.6 hours total length

Prefer offline learning? Download all 54 video lectures and project files for free.
Download Free
U01M02-Foundations-to-Build-a-Large-Language-Model-From-Scratch
Preview
6m
U01M01-Python-Environment-Setup-Video
Preview
29m
U02M03-Converting-tokens-into-token-IDs
12m
U02M02-Tokenizing-text
36m
U02M04-Adding-special-context-tokens
10m
U02M05-Byte-pair-encoding
22m
U02M07-Creating-token-embeddings
11m
U02M06-Data-sampling-with-a-sliding-window
29m
U02M08-Encoding-word-positions
16m
U02M01-Prerequisites-to-Chapter-2
1h 11m
U03M03-A-simple-self-attention-mechanism-without-trainable-weights-Part-2
18m
U03M02-A-simple-self-attention-mechanism-without-trainable-weights-Part-1
55m
U03M01-Prerequisites-to-Chapter-3
1h 8m
U03M05-Implementing-a-compact-self-attention-Python-class
11m
U03M07-Masking-additional-attention-weights-with-dropout
5m
U03M06-Applying-a-causal-attention-mask
18m
U03M04-Computing-the-attention-weights-step-by-step
19m
U03M08-Implementing-a-compact-causal-self-attention-class
13m
U03M09-Stacking-multiple-single-head-attention-layers
14m
U04M02-Coding-an-LLM-architecture
19m
U03M10-Implementing-multi-head-attention-with-weight-splits
39m
U04M03-Normalizing-activations-with-layer-normalization
25m
U04M05-Adding-shortcut-connections
13m
U04M04-Implementing-a-feed-forward-network-with-GELU-activations
33m
U04M06-Connecting-attention-and-linear-layers-in-a-transformer-block
19m
U04M07-Coding-the-GPT-model
21m
U04M08-Generating-text
20m
U04M01-Prerequisites-to-Chapter-4
1h 2m
U05M01-Prerequisites-to-Chapter-5
20m
U05M02-Using-GPT-to-generate-text
26m
U05M03-Calculating-the-text-generation-loss-cross-entropy-and-perplexity
34m
U05M06-Decoding-strategies-to-control-randomness
7m
U05M07-Temperature-scaling
14m
U05M04-Calculating-the-training-and-validation-set-losses
33m
U05M08-Top-k-sampling
9m
U05M09-Modifying-the-text-generation-function
11m
U05M05-Training-an-LLM
52m
U05M10-Loading-and-saving-model-weights-in-PyTorch
7m
U05M11-Loading-pretrained-weights-from-OpenAI
38m
U06M01-Prerequisites-to-Chapter-6
52m
U06M02-Preparing-the-dataset
36m
U06M04-Initializing-a-model-with-pretrained-weights
14m
U06M03-Creating-data-loaders
18m
U06M05-Adding-a-classification-head
27m
U06M08-Using-the-LLM-as-a-spam-classifier
11m
U06M06-Calculating-the-classification-loss-and-accuracy
22m
U07M01-Preparing-a-dataset-for-supervised-instruction-fine-tuning
16m
U06M07-Fine-tuning-the-model-on-supervised-data
1h
U07M03-Creating-data-loaders-for-an-instruction-dataset
10m
U07M04-Loading-a-pretrained-LLM
8m
U07M06-Extracting-and-saving-responses
16m
U07M05-Fine-tuning-the-LLM-on-instruction-data
36m
U07M07-Evaluating-the-fine-tuned-LLM
37m
U07M02-Organizing-data-into-training-batches
26m

Requirements

  • Python Environment Setup – Get your development environment perfect from day one
  • Python Fundamentals – Master loops, conditionals, variables, functions, methods, and classes
  • Vector Mathematics – Build intuitive understanding of the math behind AI
  • PyTorch Essentials – From basic tensors to advanced operations
  • Neural Network Foundations – Dot products, matrix multiplication, and activation functions
  • Deep Learning Building Blocks – Linear layers, loss functions, backpropagation, and gradient calculation

Description

Master and Build Large Language Models. This course helps participants become a professional modeler by learning the concepts and building a large language model. This course teaches the best way to understand large language models (LLMs) by building them. Led by experienced AI researcher Sebastian Raschka, participants will learn the inner workings of these models. In this course, you will learn how to code all the parts of an LLM, prepare a suitable dataset, fine-tune the model for text classification, use human feedback, and load pre-trained weights. This course is designed for software engineers, data scientists, and machine learning researchers who plan to build or adapt LLMs. It also includes six prerequisite videos by AI expert Abhinav Kimothy that cover Python basics, vector mathematics, PyTorch essentials, neural networks, and deep learning building blocks. These videos cover setting up a Python environment, mastering basic concepts, understanding the mathematics of AI, learning PyTorch operations, and the basics of neural networks. This comprehensive course ensures that participants, regardless of their initial knowledge level, will succeed in building large language models.

Instructor

S

Sebastian Raschka

Specialist in Other Professional Courses

Passionate educator focused on real-world practical skills, modern frameworks, and production-ready engineering practices. Delivering step-by-step masterclasses accessible to learners globally on MJ Accedemy.

Recommended Curriculum

Students Also Viewed