# llm-course | Maxime Labonne | Knowledge Base | Instagit

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

GitHub Stars: 75.9k

Repository: https://github.com/mlabonne/llm-course

---

## Articles

### [How to Leverage Axolotl for LLM Training and Fine-Tuning: A Complete Guide](/mlabonne/llm-course/axolotl-llm-training)

Learn to leverage Axolotl for LLM training and fine-tuning. This guide covers data preprocessing, quantization, and distributed scaling with a single config file.

- Tags: how-to-guide
- Published: 2026-03-01

### [Benefits of Using Unsloth for LLM Acceleration: A Technical Deep Dive](/mlabonne/llm-course/unsloth-llm-acceleration)

Discover Unsloth LLM acceleration benefits. Train 7B and 13B models utilizing up to 75% less VRAM with 4-bit quantization and LoRA on free Colab GPUs.

- Tags: deep-dive
- Published: 2026-03-01

### [Using QLoRA for Efficient LLM Fine-Tuning: A Complete Implementation Guide](/mlabonne/llm-course/qlora-llm-fine-tuning)

Master efficient LLM fine-tuning with QLoRA. This guide shows how to reduce GPU memory by 75% for 7B+ models on consumer GPUs with minimal performance loss. Learn implementation now.

- Tags: how-to-guide
- Published: 2026-03-01

### [Optimizing LLM Inference Speed and Performance with the LLM Course](/mlabonne/llm-course/optimizing-llm-inference)

Learn to optimize LLM inference speed and performance with the mlabonne/llm-course repository. Explore quantization, model merging, and speculative decoding for faster, high-quality results.

- Tags: performance
- Published: 2026-03-01

### [Designing and Implementing LLM Agents: A Practical Guide Using the LLM-Course Repository](/mlabonne/llm-course/designing-llm-agents)

Learn to design and implement LLM agents that use tools and retrieval systems for autonomous tasks. Explore practical examples with LangChain and vector databases in the mlabonne/llm-course repository.

- Tags: how-to-guide
- Published: 2026-03-01

### [Building Retrieval-Augmented Generation (RAG) Systems: A Complete Guide Using the LLM Course Repository](/mlabonne/llm-course/building-rag-systems)

Master building Retrieval-Augmented Generation RAG systems with the comprehensive mlabonne/llm-course. Learn via hands-on Colab notebooks and a structured curriculum.

- Tags: tutorial
- Published: 2026-03-01

### [Strategies for Running LLMs Efficiently: 8 Optimization Techniques from the LLM Course](/mlabonne/llm-course/running-llms-efficiently)

Discover 8 effective strategies for running LLMs efficiently. Optimize inference with quantization, KV caching, speculative decoding, and more to reduce latency and memory.

- Tags: how-to-guide
- Published: 2026-03-01

### [How Quantization Reduces LLM Memory Footprint and Improves Inference: A Technical Guide](/mlabonne/llm-course/llm-quantization-techniques)

Discover how LLM quantization slashes VRAM usage by converting weights to INT8 or INT4. Boost inference speed with this technical guide.

- Tags: deep-dive
- Published: 2026-03-01

### [Methods for Evaluating the Performance of Large Language Models: 3 Essential Approaches](/mlabonne/llm-course/evaluating-llm-performance)

Discover 3 essential methods for evaluating large language models automate benchmarks human evaluation and model based scoring for robust performance assessment

- Tags: deep-dive
- Published: 2026-03-01

### [How to Align LLM Preferences Using DPO, GRPO, and PPO](/mlabonne/llm-course/llm-preference-alignment-dpo-grpo-ppo)

Learn how to align LLM preferences using DPO, GRPO, and PPO. Explore these RLHF methods for better language model control and understand their key differences for optimal model alignment.

- Tags: deep-dive
- Published: 2026-03-01

### [Implementing Supervised Fine-Tuning (SFT) for LLMs: A Complete Guide with TRL, Unsloth, and Axolotl](/mlabonne/llm-course/supervised-fine-tuning-sft-llms)

Learn Supervised Fine-Tuning SFT for LLMs with TRL Unsloth and Axolotl. Convert pre-trained models into instruction followers efficiently reducing VRAM.

- Tags: how-to-guide
- Published: 2026-03-01

### [Creating Post-Training Datasets for LLMs: 5 Proven Strategies for High-Quality Data Curation](/mlabonne/llm-course/post-training-dataset-creation)

Discover 5 proven strategies for creating high-quality post-training datasets for LLMs. Learn to standardize, generate, enrich, deduplicate, and filter data effectively.

- Tags: best-practices
- Published: 2026-03-01

### [How Does Pre-Training Work for Large Language Models: From Data to Foundation](/mlabonne/llm-course/llm-pretraining-process)

Discover how large language models master language through pre-training. Learn about the process from data selection to foundation model creation and explore advanced techniques used in LLM development.

- Tags: deep-dive
- Published: 2026-03-01

### [Key Components of LLM Architecture: A Deep Dive into Modern Transformer Design](/mlabonne/llm-course/llm-architecture-components)

Explore the key components of LLM architecture including the Transformer backbone, tokenizers, attention mechanisms, and sampling strategies for advanced text generation.

- Tags: deep-dive
- Published: 2026-03-01

### [Understanding Core Natural Language Processing (NLP) Concepts for LLMs](/mlabonne/llm-course/nlp-concepts-for-llms)

Unlock the power of LLMs by mastering core NLP concepts. Explore the five-stage NLP pipeline including preprocessing, feature extraction, and sequential architectures for transformative text understanding.

- Tags: tutorial
- Published: 2026-03-01

### [What Are Neural Networks and How Do They Apply to LLMs?](/mlabonne/llm-course/neural-networks-for-llms)

Discover neural networks, the layered math structures powering LLMs. Learn how they process text using learned parameters and transformations.

- Tags: deep-dive
- Published: 2026-03-01

### [How to Use Python for Training and Evaluating LLMs: A Complete Workflow Guide](/mlabonne/llm-course/python-for-llm-training)

Learn to train and evaluate LLMs in Python with Hugging Face Transformers and PEFT. Master data prep, fine-tuning, and standardized benchmarking for efficient LLM development.

- Tags: how-to-guide
- Published: 2026-03-01

### [Essential Math Concepts for LLM Development: The Three Pillars Explained](/mlabonne/llm-course/math-for-llm-development)

Master essential math for LLM development: Linear Algebra, Calculus, and Probability & Statistics. Understand data encoding, parameter optimization, and probabilistic text generation.

- Tags: deep-dive
- Published: 2026-03-01

### [LLM Scientist vs LLM Engineer: Understanding the Key Differences](/mlabonne/llm-course/llm-scientist-vs-engineer)

Discover the core differences between an LLM Scientist and an LLM Engineer. Learn how scientists advance models and engineers deploy them in production.

- Tags: deep-dive
- Published: 2026-03-01

### [How to Get Started with LLM Fundamentals for Machine Learning: A Complete Roadmap](/mlabonne/llm-course/llm-fundamentals-getting-started)

Master LLM fundamentals for machine learning. Follow this roadmap covering math, Python, and neural networks with practical code examples from mlabonne/llm-course.

- Tags: getting-started
- Published: 2026-03-01