Building LLMs for Production
0h 0m 0s
English
Paid
Course description
"Creating LLM for Production" is a practical 470-page guide (updated in October 2024) designed for developers and specialists who want to go beyond prototyping and build reliable, industry-ready applications based on large language models.
The book explains the fundamentals of how LLMs work and thoroughly examines key techniques: advanced prompting, Retrieval-Augmented Generation (RAG), model fine-tuning, evaluation methods, and deployment strategies. Readers gain access to interactive Colab notebooks, real code examples, and case studies demonstrating how to integrate LLMs into products and workflows in practice. Special attention is given to issues of security, monitoring, optimization, and cost reduction.
Books
Read Book Building LLMs for Production
| # | Title |
|---|---|
| 1 | Table of Contents |
| 2 | About The Book |
| 3 | Introduction |
| 4 | Why Prompt Engineering, Fine-Tuning, and RAG? |
| 5 | Coding Environment and Packages |
| 6 | A Brief History of Language Models |
| 7 | What are Large Language Models? |
| 8 | Building Blocks of LLMs |
| 9 | Tutorial: Translation with LLMs (GPT-3.5 API) |
| 10 | Tutorial: Control LLMs Output with Few-Shot Learning |
| 11 | Recap |
| 12 | Understanding Transformers |
| 13 | Transformer Model’s Design Choices |
| 14 | Transformer Architecture Optimization Techniques |
| 15 | The Generative Pre-trained Transformer (GPT) Architecture |
| 16 | Introduction to Large Multimodal Models |
| 17 | Proprietary vs. Open Models vs. Open-Source Language Models |
| 18 | Applications and Use-Cases of LLMs |
| 19 | Recap |
| 20 | Understanding Hallucinations and Bias |
| 21 | Reducing Hallucinations by Controlling LLM Outputs |
| 22 | Evaluating LLM Performance |
| 23 | Recap |
| 24 | Prompting and Prompt Engineering |
| 25 | Prompting Techniques |
| 26 | Prompt Injection and Security |
| 27 | Recap |
| 28 | Why RAG? |
| 29 | Building a Basic RAG Pipeline from Scratch |
| 30 | Recap |
| 31 | LLM Frameworks |
| 32 | LangChain Introduction |
| 33 | Tutorial 1: Building LLM-Powered Applications with LangChain |
| 34 | Tutorial 2: Building a News Articles Summarizer |
| 35 | LlamaIndex Introduction |
| 36 | LangChain vs. LlamaIndex vs. OpenAI Assistants |
| 37 | Recap |
| 38 | What are LangChain Prompt Templates |
| 39 | Few-Shot Prompts and Example Selectors |
| 40 | What are LangChain Chains |
| 41 | Tutorial 1: Managing Outputs with Output Parsers |
| 42 | Tutorial 2: Improving Our News Articles Summarizer |
| 43 | Tutorial 3: Creating Knowledge Graphs from Textual Data: Finding Hidden Connections |
| 44 | Recap |
| 45 | LangChain’s Indexes and Retrievers |
| 46 | Data Ingestion |
| 47 | Text Splitters |
| 48 | Similarity Search and Vector Embeddings |
| 49 | Tutorial 1: A Customer Support Q&A Chatbot |
| 50 | Tutorial 2: A YouTube Video Summarizer Using Whisper and LangChain |
| 51 | Tutorial 3: A Voice Assistant for Your Knowledge Base |
| 52 | Tutorial 4: Preventing Undesirable Outputs with the Self-Critique Chain |
| 53 | Tutorial 5: Preventing Undesirable Outputs from a Customer Service Chatbot |
| 54 | Recap |
| 55 | From Proof of Concept to Product: Challenges of RAG Systems |
| 56 | Advanced RAG Techniques with LlamaIndex |
| 57 | RAG - Metrics & Evaluation |
| 58 | LangChain LangSmith and LangChain Hub |
| 59 | Recap |
| 60 | What are Agents: Large Models as Reasoning Engines |
| 61 | An Overview of AutoGPT and BabyAGI |
| 62 | The Agent Simulation Projects in LangChain |
| 63 | Tutorial 1: Building Agents for Analysis Report Creation |
| 64 | Tutorial 2: Query and Summarize a DB with LlamaIndex |
| 65 | Tutorial 3: Building Agents with OpenAI Assistants |
| 66 | Tutorial 4: LangChain OpenGPT |
| 67 | Tutorial 5: Multimodal Financial Document Analysis from PDFs |
| 68 | Recap |
| 69 | Understanding Fine-Tuning |
| 70 | Low-Rank Adaptation (LoRA) |
| 71 | Tutorial 1: SFT with LoRA |
| 72 | Tutorial 2: Using SFT and LoRA for Financial Sentiment |
| 73 | Tutorial 3: Fine-Tuning a Cohere LLM with Medical Data |
| 74 | Reinforcement Learning from Human Feedback |
| 75 | Tutorial 4: Improving LLMs with RLHF |
| 76 | Recap |
| 77 | Model Distillation and Teacher-Student Models |
| 78 | LLM Deployment Optimization: Quantization, Pruning, and Speculative Decoding |
| 79 | Tutorial: Deploying a Quantized LLM on a CPU on Google Cloud Platform (GCP) |
| 80 | Deploying Open-Source LLMs on Cloud Providers |
| 81 | Recap |
| 82 | Conclusion |
| 83 | Further Reading and Courses |
Comments
0 commentsWant to join the conversation?
Sign in to commentSimilar courses
Build AI-Powered Apps – An AI Course for Developers
Sources: codewithmosh (Mosh Hamedani)
AI is everywhere - but can you really create applications with it? Most developers have tried ChatGPT. Some have even inserted pieces...
7 hours 3 minutes 31 seconds
Full-Stack Project with Claude Code
Sources: Mckay Wrigley (takeoff)
In this workshop, participants step by step create an MVP clone of FigJam - a visual collaboration editor - using Claude Code, Opus 4, Cursor IDE, and...
1 hour 12 minutes 14 seconds
The NotebookLM Guide: Your AI-Powered Productivity Assistant
Sources: zerotomastery.io
Learn to use NotebookLM from Google to simplify research, analyze content, and boost productivity. From automatic summaries to...
2 hours 3 minutes 22 seconds
How To Connect, Code & Debug Supabase With Bolt
Sources: newline (ex fullstack.io)
This workshop is a continuation of the course "Overnight Fullstack Applications". In the recording, you will learn how to connect your applications in Bolt...
42 minutes
Claude Code
Sources: Mckay Wrigley (takeoff)
Claude Code is a course that teaches how to use the intelligent assistant (AI) from Anthropic for programming directly in the terminal. It helps write...
2 hours 23 minutes 22 seconds