# Hands-On Large Language Models

## Docs

- [Welcome to Hands-On Large Language Models](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/introduction.md): Official documentation for the O'Reilly book featuring practical tutorials and visual guides for understanding and building with LLMs
- [Environment Setup](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/setup.md): Complete guide to setting up your development environment for working with the Hands-On Large Language Models code examples
- [Prerequisites](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/prerequisites.md): Required background knowledge and recommended preparatory resources for getting the most out of Hands-On Large Language Models
- [Chapter 1: Introduction to Language Models](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-01-introduction.md): Exploring the exciting field of Language AI with hands-on examples using state-of-the-art models
- [Chapter 2: Tokens and Token Embeddings](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-02-tokens-embeddings.md): Exploring tokens and embeddings as an integral part of building and understanding LLMs
- [Chapter 3: Looking Inside Transformer LLMs](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-03-inside-llms.md): An extensive look into the transformer architecture of generative LLMs and how they process information
- [Chapter 4: Text Classification](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-04-text-classification.md): Classifying text with both representative and generative models
- [Chapter 5: Text Clustering and Topic Modeling](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-05-clustering-topics.md): Clustering documents using a wide variety of language models
- [Chapter 6: Prompt Engineering](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-06-prompt-engineering.md): Methods for improving LLM outputs through effective prompt engineering techniques
- [Chapter 7: Advanced Text Generation Techniques and Tools](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-07-advanced-generation.md): Going beyond prompt engineering with chains, memory, and agents
- [Chapter 8: Semantic Search and RAG](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-08-semantic-search.md): Exploring semantic search, vector databases, and retrieval-augmented generation for LLM applications
- [Chapter 9: Multimodal Large Language Models](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-09-multimodal.md): Adding vision capabilities to large language models through CLIP, BLIP-2, and other multimodal architectures
- [Creating Text Embedding Models](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-10-embedding-models.md): Learn how to train and fine-tune text embedding models from scratch using different loss functions and evaluation strategies.
- [Fine-Tuning BERT for Classification](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-11-finetuning-bert.md): Master supervised and few-shot classification by fine-tuning BERT models with different strategies including layer freezing and parameter-efficient methods.
- [Fine-Tuning Generation Models](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/chapters/chapter-12-finetuning-generation.md): Master the two-step approach for fine-tuning generative LLMs using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) with QLoRA.
- [Visual Guide to Quantization](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/quantization.md): Learn how quantization reduces model size while maintaining performance through detailed visual explanations
- [Visual Guide to Mamba and State Space Models](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/mamba.md): Explore an alternative to Transformers through state space models and the Mamba architecture
- [Visual Guide to Mixture of Experts](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/mixture-of-experts.md): Understand how MoE architectures enable efficient scaling to trillion-parameter models
- [Visual Guide to Reasoning LLMs](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/reasoning-llms.md): Explore how modern LLMs perform complex reasoning through extended thinking and search
- [The Illustrated DeepSeek-R1](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/deepseek-r1.md): A detailed visual breakdown of DeepSeek-R1, the open-source reasoning model rivaling OpenAI o1
- [Visual Guide to LLM Agents](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/agents.md): Learn how LLMs become autonomous agents that can plan, use tools, and accomplish complex tasks
- [The Illustrated Stable Diffusion](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/stable-diffusion.md): A visual guide to understanding how Stable Diffusion generates images from text
- [How Transformer LLMs Work - DeepLearning.AI Course](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/advanced/deeplearning-ai-course.md): Interactive course bringing the book to life through highly animated visualizations
- [About the Authors](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/resources/about-authors.md): Meet Jay Alammar and Maarten Grootendorst, the authors of Hands-On Large Language Models
- [How to Cite This Book](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/resources/citation.md): Citation formats and BibTeX entry for Hands-On Large Language Models
- [Contributing to the Repository](https://mintlify.wiki/HandsOnLLM/Hands-On-Large-Language-Models/resources/contributing.md): How to contribute code, report issues, and improve the Hands-On Large Language Models repository


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.