Skip to content

2-Week GenAI & LLM Engineering Crash Training

LoRA and QLoRA

KirkYagami/2-Week-GenAI-LLM-Engineering-Crash-Training

2-Week GenAI & LLM Engineering Crash Training

KirkYagami/2-Week-GenAI-LLM-Engineering-Crash-Training

Home
Notebooks
Week 01 — LLM Fundamentals
Week 01 — LLM Fundamentals
- Overview
- Day 01 — How LLMs Work & Prompt Engineering
  Day 01 — How LLMs Work & Prompt Engineering
  - Part 1 — How LLMs Work
    Part 1 — How LLMs Work
    
    Agenda
    
    Transformers and Attention
    
    Tokenization
    
    Context Windows
    
    How LLMs Generate Text
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Prompt Engineering
    Part 2 — Prompt Engineering
    
    Agenda
    
    Zero-Shot and Few-Shot
    
    Chain-of-Thought
    
    Structured Output
    
    System Prompts
    
    Advanced Prompt Patterns
    
    Practice Exercises
    
    Interview Questions
- Day 02 — APIs & Embeddings
  Day 02 — APIs & Embeddings
  - Part 1 — OpenAI and Anthropic APIs
    Part 1 — OpenAI and Anthropic APIs
    
    Agenda
    
    OpenAI Chat Completions
    
    Vision and Multimodal
    
    Tool Use with OpenAI
    
    Anthropic Messages API
    
    Cost and Rate Limits
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Embeddings and Semantic Search
    Part 2 — Embeddings and Semantic Search
    
    Agenda
    
    What Are Embeddings
    
    Embedding Models
    
    Cosine Similarity
    
    Vector Search
    
    Semantic Search Pipeline
    
    Practice Exercises
    
    Interview Questions
- Day 03 — RAG & Vector Databases
  Day 03 — RAG & Vector Databases
  - Part 1 — RAG Basics
    Part 1 — RAG Basics
    
    Agenda
    
    What is RAG
    
    Chunking Strategies
    
    Retrieval and Augmentation
    
    RAG Pipeline End-to-End
    
    RAG vs Fine-Tuning
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Vector Databases
    Part 2 — Vector Databases
    
    Agenda
    
    Vector DB Overview
    
    ChromaDB
    
    Pinecone
    
    Qdrant
    
    Indexing and Filtering
    
    Hybrid Search
    
    Practice Exercises
    
    Interview Questions
- Day 04 — Evaluation & Responsible AI
  Day 04 — Evaluation & Responsible AI
  - Part 1 — LLM Evaluation
    Part 1 — LLM Evaluation
    
    Agenda
    
    Evaluation Overview
    
    RAGAS Framework
    
    Hallucination and Faithfulness
    
    Relevance Metrics
    
    Human Evaluations
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Responsible AI and Safety
    Part 2 — Responsible AI and Safety
    
    Agenda
    
    Jailbreaks and Prompt Injection
    
    Guardrails
    
    Content Filtering
    
    Bias and Fairness
    
    Practice Exercises
    
    Interview Questions
- Day 05 — Hugging Face & Local LLMs
  Day 05 — Hugging Face & Local LLMs
  - Part 1 — Hugging Face Ecosystem
    Part 1 — Hugging Face Ecosystem
    
    Agenda
    
    Hugging Face Hub
    
    Transformers Library
    
    Inference API
    
    Spaces
    
    Datasets and Model Cards
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Local LLMs
    Part 2 — Local LLMs
    
    Agenda
    
    Why Run Locally
    
    Ollama
    
    llama.cpp
    
    Quantization
    
    When to Run Locally
    
    Practice Exercises
    
    Interview Questions
Week 02 — Building LLM Applications
Week 02 — Building LLM Applications
- Overview
- Day 01 — LangChain & Advanced RAG
  Day 01 — LangChain & Advanced RAG
  - Part 1 — LangChain Fundamentals
    Part 1 — LangChain Fundamentals
    
    Agenda
    
    LangChain Overview
    
    Chains and Prompts
    
    Memory
    
    LCEL
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Advanced RAG
    Part 2 — Advanced RAG
    
    Agenda
    
    Reranking
    
    HyDE
    
    Multi-Query Retrieval
    
    Contextual Compression
    
    Advanced RAG Patterns
    
    Practice Exercises
    
    Interview Questions
- Day 02 — Fine-Tuning & Function Calling
  Day 02 — Fine-Tuning & Function Calling
  - Part 1 — Fine-Tuning
    Part 1 — Fine-Tuning
    
    Agenda
    
    Fine-Tuning Overview
    
    LoRA and QLoRA
    
    PEFT
    
    Training Data Preparation
    
    When to Fine-Tune
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Function Calling and Tool Use
    Part 2 — Function Calling and Tool Use
    
    Agenda
    
    Function Calling Overview
    
    OpenAI Tools API
    
    Anthropic Tool Use
    
    Structured Extraction
    
    Parallel Tool Calls
    
    Practice Exercises
    
    Interview Questions
- Day 03 — Agents & LangGraph
  Day 03 — Agents & LangGraph
  - Part 1 — AI Agents
    Part 1 — AI Agents
    
    Agenda
    
    What Are AI Agents
    
    The ReAct Loop
    
    Planning Strategies
    
    Tool-Calling Agents
    
    Memory Strategies
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — LangGraph
    Part 2 — LangGraph
    
    Agenda
    
    LangGraph Overview
    
    Nodes and Edges
    
    Stateful Graphs
    
    Conditional Routing
    
    Multi-Agent Orchestration
    
    Practice Exercises
    
    Interview Questions
- Day 04 — LLMOps & Deployment
  Day 04 — LLMOps & Deployment
  - Part 1 — LLMOps
    Part 1 — LLMOps
    
    Agenda
    
    Tracing and Logging
    
    LangSmith
    
    Cost Tracking
    
    Latency Optimization
    
    Observability
    
    Practice Exercises
    
    Interview Questions
  - Part 2 — Deployment
    Part 2 — Deployment
    
    Agenda
    
    FastAPI Wrappers
    
    Streaming Responses
    
    Async Patterns
    
    Serverless Deployment
    
    Caching Strategies
    
    Practice Exercises
    
    Interview Questions
- Day 05 — Capstone & Interview
  Day 05 — Capstone & Interview
  - Part 1 — Capstone Project
    Part 1 — Capstone Project
    
    Agenda
    
    Project Brief
    
    Architecture Design
    
    Implementation
    
    Evaluation and Testing
    
    Presentation Guide
    
    Submission Checklist
  - Part 2 — Mock Interview and Portfolio
    Part 2 — Mock Interview and Portfolio
    
    Agenda
    
    Resume Checklist
    
    Portfolio and GitHub
    
    Technical Interview Questions
    
    System Design Practice
    
    Mock Interview Script
Projects
Projects
- RAG Q&A Chatbot
  RAG Q&A Chatbot
- AI Writing Assistant
  AI Writing Assistant
- Document Summarizer with Eval
  Document Summarizer with Eval
- Function-Calling Data Extractor
  Function-Calling Data Extractor
- LangGraph Research Agent
  LangGraph Research Agent
- Fine-Tuned Classifier
  Fine-Tuned Classifier
Cheat Sheets
Cheat Sheets
- OpenAI API
- Anthropic API
- LangChain
- LangGraph
- ChromaDB
- Prompt Engineering
- RAG
- Fine-Tuning
- AI Agents
- LLMOps
Interview Prep
Interview Prep
- Overview
- Prompt Engineering
  Prompt Engineering
- RAG and Vector Search
  RAG and Vector Search
- LLM APIs
  LLM APIs
- Agents and LangGraph
  Agents and LangGraph
- Fine-Tuning
  Fine-Tuning
- LLMOps
  LLMOps
- System Design
  System Design
- Mock Interview Simulator
Glossary
Progress Tracker
Assignments
Assignments
- Week 01
- Week 02
Resources
Resources

LoRA and QLoRA¶