AI Engineer Core Track: LLM Engineering, RAG, QLoRA, Agents

NEW Week 1 – Build Your First LLM Product Exploring Top Models
1 Day 1 – Running Your First LLM Locally with Ollama and Open Source Models
2 Day 1 – Spanish Tutor Demo with Open-Source Models & Course Overview
3 Day 1 – Setting Up Your LLM Development Environment with Cursor and UV
4 Day 1 – Setting Up Your PC Development Environment with Git and Cursor
5 Day 1 – Mac Setup Installing Git, Cloning the Repo, and Cursor IDE
6 Day 1 – Installing UV and Setting Up Your Cursor Development Environment
7 Day 1 – Setting Up Your OpenAI API Key and Environment Variables
8 Day 1 – Installing Cursor Extensions and Setting Up Your Jupyter Notebook
9 Day 1 – Running Your First OpenAI API Call and System vs User Prompts
10 Day 1 – Building a Website Summarizer with OpenAI Chat Completions API
11 Day 1 – Hands-On Exercise Building Your First OpenAI API Call from Scratch
12 Day 2 – LLM Engineering Building Blocks Models, Tools & Techniques
13 Day 2 – Your 8-Week Journey From Chat Completions API to LLM Engineer
14 Day 2 – Frontier Models OpenAI GPT, Claude, Gemini & Grok Compared
15 Day 2 – Open-Source LLMs LLaMA, Mistral, DeepSeek, and Ollama
16 Day 2 – Chat Completions API HTTP Endpoints vs OpenAI Python Client
17 Day 2 – Using the OpenAI Python Client with Multiple LLM Providers
18 Day 2 – Running Ollama Locally with OpenAI-Compatible Endpoints
19 Day 3 – Base, Chat, and Reasoning Models Understanding LLM Types
20 Day 3 – Frontier Models GPT, Claude, Gemini & Their Strengths and Pitfalls
21 Day 3 – Testing ChatGPT-5 and Frontier LLMs Through the Web UI
22 Day 3 – Testing Claude, Gemini, Grok & DeepSeek with ChatGPT Deep Research
23 Day 3 – Agentic AI in Action Deep Research, Claude Code, and Agent Mode
24 Day 3 – Frontier Models Showdown Building an LLM Competition Game
25 Day 4 – Understanding Transformers The Architecture Behind GPT and LLMs
26 Day 4 – From LSTMs to Transformers Attention, Emergent Intelligence & Agentic A
27 Day 4 – Parameters From Millions to Trillions in GPT, LLaMA & DeepSeek
28 Day 4 – What Are Tokens From Characters to GPT’s Tokenizer
29 Day 4 – Understanding Tokenization How GPT Breaks Down Text into Tokens
30 Day 4 – Tokenizing with tiktoken and Understanding the Illusion of Memory
31 Day 4 – Context Windows, API Costs, and Token Limits in LLMs
32 Day 5 – Building a Sales Brochure Generator with OpenAI Chat Completions API
33 Day 5 – Building JSON Prompts and Using OpenAI’s Chat Completions API
34 Day 5 – Chaining GPT Calls Building an AI Company Brochure Generator
35 Day 5 – Building a Brochure Generator with GPT-4 and Streaming Results
36 Day 5 – Business Applications, Challenges & Building Your AI Tutor

NEW Week 2 – Build a Multi-Modal Chatbot LLMs, Gradio UI, and Agents
37 Day 1 – Connecting to Multiple Frontier Models with APIs (OpenAI, Claude, Gemini
38 Day 1 – Testing GPT-5 Models with Reasoning Effort and Scaling Puzzles
39 Day 1 – Testing Claude, GPT-5, Gemini & DeepSeek on Brain Teasers
40 Day 1 – Local Models with Ollama, Native APIs, and OpenRouter Integration
41 Day 1 – LangChain vs LiteLLM Choosing the Right LLM Framework
42 Day 1 – LLM vs LLM Building Multi-Model Conversations with OpenAI & Claude
43 Day 2 – Building Data Science UIs with Gradio (No Front-End Skills Required)
44 Day 2 – Building Your First Gradio Interface with Callbacks and Sharing
45 Day 2 – Building Gradio Interfaces with Authentication and GPT Integration
46 Day 2 – Markdown Responses and Streaming with Gradio and OpenAI
47 Day 2 – Building Multi-Model Gradio UIs with GPT and Claude Streaming
48 Day 3 – Building Chat UIs with Gradio Your First Conversational AI Assistant
49 Day 3 – Building a Streaming Chatbot with Gradio and OpenAI API
50 Day 3 – System Prompts, Multi-Shot Prompting, and Your First Look at RAG
51 Day 4 – How LLM Tool Calling Really Works (No Magic, Just Prompts)
52 Day 4 – Common Use Cases for LLM Tools and Agentic AI Workflows
53 Day 4 – Building an Airline AI Assistant with Tool Calling in OpenAI and Gradio
54 Day 4 – Handling Multiple Tool Calls with OpenAI and Gradio
55 Day 4 – Building Tool Calling with SQLite Database Integration
56 Day 5 – Introduction to Agentic AI and Building Multi-Tool Workflows
57 Day 5 – How Gradio Works Building Web UIs from Python Code
58 Day 5 – Building Multi-Modal Apps with DALL-E 3, Text-to-Speech, and Gradio Bloc
59 Day 5 – Running Your Multimodal AI Assistant with Gradio and Tools

NEW Week 3 – Open-Source Gen AI Automated Solutions with HuggingFace
60 Day 1 – Introduction to Hugging Face Platform Models, Datasets, and Spaces
61 Day 1 – HuggingFace Libraries Transformers, Datasets, and Hub Explained
62 Day 1 – Introduction to Google Colab and Cloud GPUs for AI Development
63 Day 1 – Getting Started with Google Colab Setup, Runtime, and Free GPU Access
64 Day 1 – Setting Up Google Colab with Hugging Face and Running Your First Model
65 Day 1 – Running Stable Diffusion and FLUX on Google Colab GPUs
66 Day 2 – Introduction to Hugging Face Pipelines for Quick AI Inference
67 Day 2 – HuggingFace Pipelines API for Sentiment Analysis on Colab T4 GPU
68 Day 2 – Named Entity Recognition, Q&A, and Hugging Face Pipeline Tasks
69 Day 2 – Hugging Face Pipelines Image, Audio & Diffusion Models in Colab
70 Day 3 – Tokenizers How LLMs Convert Text to Numbers
71 Day 3 – Tokenizers in Action Encoding and Decoding with Llama 3.1
72 Day 3 – How Chat Templates Work LLaMA Tokenizers and Special Tokens
73 Day 3 – Comparing Tokenizers Phi-4, DeepSeek, and QWENCoder in Action
74 Day 4 – Deep Dive into Transformers, Quantization, and Neural Networks
75 Day 4 – Working with Hugging Face Transformers Low-Level API and Quantization
76 Day 4 – Inside LLaMA PyTorch Model Architecture and Token Embeddings
77 Day 4 – Inside LLaMA Decoder Layers, Attention, and Why Non-Linearity Matters
78 Day 4 – Running Open Source LLMs Phi, Gemma, Qwen & DeepSeek with Hugging Face
79 Day 5 – Visualizing Token-by-Token Inference in GPT Models
80 Day 5 – Building Meeting Minutes from Audio with Whisper and Google Colab
81 Day 5 – Building Meeting Minutes with OpenAI Whisper and LLaMA 3.2
82 Day 5 – Week 3 Wrap-Up Build a Synthetic Data Generator with Open Source Models

New Week 4 – LLM Showdown Evaluating Models for Code Gen & Business Tasks
83 Day 1 – Choosing the Right LLM Model Selection Strategy and Basics
84 Day 1 – The Chinchilla Scaling Law Parameters, Training Data and Why It Matters
85 Day 1 – Understanding AI Model Benchmarks GPQA, MMLU-Pro, and HLE
86 Day 1 – Limitations of AI Benchmarks Data Contamination and Overfitting
87 Day 1 – Build a Connect Four Leaderboard (Reasoning Benchmark)
88 Day 2 – Navigating AI Leaderboards Artificial Analysis, HuggingFace & More
89 Day 2 – Artificial Analysis Deep Dive Model Intelligence vs Cost Comparison
90 Day 2 – Vellum, SEAL, and LiveBench Essential AI Model Leaderboards
91 Day 2 – LM Arena Blind Testing AI Models with Community Elo Ratings
92 Day 2 – Commercial Use Cases Automation, Augmentation & Agentic AI
93 Day 3 – Selecting LLMs for Code Generation Python to C++ with Cursor
94 Day 3 – Selecting Frontier Models GPT-5, Claude, Grok & Gemini for C++ Code Gen
95 Day 3 – Porting Python to C++ with GPT-5 230x Performance Speedup
96 Day 3 – AI Coding Showdown GPT-5 vs Claude vs Gemini vs Groq Performance
97 Day 4 – Open Source Models for Code Generation Qwen, DeepSeek & Ollama
98 Day 4 – Building a Gradio UI to Test Python-to-C++ Code Conversion Models
99 Day 4 – Qwen 3 Coder vs GPT OSS OpenRouter Model Performance Showdown
100 Day 5 – Model Evaluation Technical Metrics vs Business Outcomes
101 Day 5 – Python to Rust Code Translation Testing Gemini 2.5 Pro with Cursor
102 Day 5 – Porting Python to Rust Testing GPT, Claude, and Qwen Models
103 Day 5 – Open Source Model Wins Rust Code Generation Speed Challenge

New Week 5 – Mastering RAG Build Advanced Solutions with Vector Embeddings
104 Day 1 – Introduction to RAG Retrieval Augmented Generation Fundamentals
105 Day 1 – Building a Simple RAG Knowledge Assistant with GPT-4-1 Nano
106 Day 1 – Building a Simple RAG System Dictionary Lookup and Context Retrieval
107 Day 1 – Vector Embeddings and Encoder LLMs The Foundation of RAG
108 Day 1 – How Vector Embeddings Represent Meaning From word2vec to Encoders
109 Day 1 – Understanding the Big Idea Behind RAG and Vector Data Stores
110 Day 2 – Vectors for RAG Introduction to LangChain and Vector Databases
111 Day 2 – Breaking Documents into Chunks with LangChain Text Splitters
112 Day 2 – Encoder Models vs Vector Databases OpenAI, BERT, Chroma & FAISS
113 Day 2 – Creating Vector Stores with Chroma and Visualizing Embeddings with t-SNE
114 Day 2 – 3D Vector Visualizations and Comparing Embedding Models
115 Day 3 – Building a Complete RAG Pipeline with LangChain and Chroma
116 Day 3 – Building a RAG Pipeline with LangChain LLM & Retriever Setup
117 Day 3 – Building RAG with LangChain Retriever and LLM Integration
118 Day 3 – Building Production RAG with Python Modules and Gradio UI
119 Day 3 – RAG with Conversation History Building a Gradio UI and Debugging Chunki
120 Day 4 – RAG Evaluations Measuring Performance and Iterating on Your Pipeline
121 Day 4 – Evaluating RAG Systems Retrieval Metrics, LLM as Judge, and Golden Data
122 Day 4 – Evaluating RAG Systems MRR, NDCG, and Test Data with Pydantic
123 Day 4 – LLM as a Judge Evaluating RAG Answers with Structured Outputs
124 Day 4 – Running RAG Evaluations with Gradio MRR, nDCG, and Test Results
125 Day 4 – Experimenting with Chunking Strategies and Embedding Models in RAG
126 Day 4 – Testing OpenAI Embeddings and Evaluating RAG Performance Gains
127 Day 5 – Advanced RAG Techniques Pre-processing, Re-ranking & Evals
128 Day 5 – Advanced RAG Techniques Chunking, Encoders, and Query Rewriting
129 Day 5 – Advanced RAG Techniques Query Expansion, Re-ranking & GraphRAG
130 Day 5 – Building Advanced RAG Without LangChain Semantic Chunking with LLMs
131 Day 5 – Creating Embeddings with Chroma, Visualizing with t-SNE, and Re-ranking
132 Day 5 – Building RAG Without LangChain Re-ranking and Query Rewriting
133 Day 5 – Building Production RAG with Query Expansion and Multiprocessing
134 Day 5 – Advanced RAG Evaluation From 0.73 to 0.91 MRR with GPT-4o
135 Day 5 – RAG Challenge Beat My Results & Build Your Knowledge Worker

New Week 6 Fine-tuning Frontier Large Language Models with LoRAQLoRA
136 Day 1 – Training, Datasets, and Generalization Your Capstone Begins
137 Day 1 – Finetuning LLMs & The Price is Right Capstone Project Intro
138 Day 1 – Curating Datasets Finding Data Sources and Building Training Sets
139 Day 1 – Curating Amazon Data with Hugging Face for Price Prediction
140 Day 1 – Exploring Amazon Dataset Distribution and Removing Duplicates
141 Day 1 – Weighted Sampling with NumPy and Uploading Datasets to Hugging Face
142 Day 2 – Five-Step Strategy for Selecting and Applying LLMs to Business Problems
143 Day 2 – The Five-Step AI Process & Productionizing with MLOps
144 Day 2 – Data Pre-processing with LLMs and Groq Batch Mode
145 Day 2 – Batch Processing with Groq API and JSONL Files for LLM Workflows
146 Day 2 – Batch Processing with Groq Running 22K LLM Requests for Under $1
147 Day 3 – Building Baseline Models with Traditional ML and XGBoost
148 Day 3 – Building Your First Baseline with Random Pricer and Scikit-learn
149 Day 3 – Baseline Models and Linear Regression with Scikit-Learn
150 Day 3 – Bag of Words and CountVectorizer for Linear Regression NLP
151 Day 3 – Random Forest and XGBoost Ensemble Models in Scikit-Learn
152 Day 4 – Training Your First Neural Network and Testing Frontier Models
153 Day 4 – Human Baseline Performance vs Machine Learning Models in PyTorch
154 Day 4 – Building Your First Neural Network with PyTorch
155 Day 4 – Testing GPT-4o-mini and Claude Opus Against Neural Networks
156 Day 4 – Testing Gemini 3, GPT-5.1, Claude 4.5 & Grok on Price Prediction
157 Day 5 – Fine-Tuning OpenAI Frontier Models with Supervised Fine-Tuning
158 Day 5 – Fine-Tuning GPT-4o Nano with OpenAI’s API for Custom Models
159 Day 5 – Fine-Tuning GPT-4o-mini-nano Running Jobs and Monitoring Training
160 Day 5 – Fine-Tuning Results When GPT-4o-mini Gets Worse, Not Better
161 Day 5 – When Fine-Tuning Frontier Models Fails & Building Deep Neural Networks
162 Day 5 – Deep Neural Network Redemption 289M Parameters vs Frontier Models

New Week 7 – Fine-tuned open-source model to compete with Frontier model
163 Day 1 – Introduction to QLoRA for Fine-Tuning Open-Source Models
164 Day 1 – LoRA Training LLaMA 3.2 with Low-Rank Adapters
165 Day 1 – LoRA Hyperparameters and QLoRA Quantization Explained
166 Day 1 – Setting Up Google Colab and Exploring LLaMA 3.2 Model Architecture
167 Day 1 – Loading Models with 8-bit and 4-bit Quantization Using QLoRA
168 Day 1 – LoRA Parameter Calculations and Model Size on Hugging Face
169 Day 2 – Preparing Your Dataset for Fine-Tuning with Token Limits
170 Day 2 – Fine-Tuning Data Prep Rounding Prices and Token Length Optimization
171 Day 2 – Preparing Hugging Face Datasets and Testing Base LLaMA 3.2 Model
172 Day 2 – Base Models vs Chat Models Understanding LLaMA Fine-Tuning
173 Day 3 – Fine-Tuning Hyperparameters QLoRA Settings and Training Config
174 Day 3 – Learning Rate, Optimizers, and Training Hyperparameters for LoRA
175 Day 3 – Setting Up Training Hyperparameters, qLoRA Config & Weights & Biases
176 Day 3 – Setting Up Weights & Biases and the HuggingFace SFT Trainer
177 Day 3 – Running Fine-Tuning with TRL and Monitoring Training in Weights & Biases
178 Day 4 – Monitoring Your Fine-Tuning Run with Weights & Biases
179 Day 4 – Full Dataset Training on Google Colab A100 with 800K Data Points
180 Day 4 – Monitoring Training Loss and Learning Rate in Weights & Biases
181 Day 4 – Analyzing Weights & Biases Results and Catching Overfitting
182 Day 4 – Managing Runs in Weights & Biases and Selecting Best Model Checkpoints
183 Day 5 – Results Day Running Inference on Fine-Tuned Models & Loss Calculation D
184 Day 5 – Cross-Entropy Loss How LLMs Calculate Probability Distributions
185 Day 5 – Testing Our Fine-Tuned LoRA Model Against GPT-4o Nano
186 Day 5 – Fine-Tuned LLaMA 3.2 Crushes GPT-5.1 and Frontier Models

New Week 8 – Build Autonomous multi agent system
187 Day 1 – Intro to Agentic AI & Serverless Deployment on Modal
188 Day 1 – Designing Agent Architectures & Modal Platform Setup
189 Day 1 – Running Python Locally and in the Cloud with Modal Remote Execution
190 Day 1 – Setting Up Modal Secrets and Deploying LLaMA Models to the Cloud
191 Day 1 – Deploying Fine-Tuned Models to Modal Cloud with Persistent Storage
192 Day 1 – Building Your First Agent with Modal Serverless AI
193 Day 2 – Building Advanced RAG with ChromaDB and Vector Stores (No LangChain)
194 Day 2 – Visualizing Chroma Vectors with t-SNE and Building a RAG Pipeline
195 Day 2 – RAG with GPT-4o vs Fine-Tuned Models Building an Ensemble
196 Day 2 – Ensemble Model Success Combining RAG, Neural Networks & Modal
197 Day 2 – Building and Testing an Ensemble Agent with Multiple LLM Calls
198 Day 3 – Structured Outputs with Pydantic and Constrained Decoding
199 Day 3 – Building a Deal Scanner with Structured Outputs and Pydantic
200 Day 3 – Structured Outputs for Parsing & Building a Pushover Notification Agent
201 Day 4 – Building Agentic AI Planning Agents with Tool Orchestration
202 Day 4 – Building an Autonomous Planner Agent with Tool Calling and GPT-4
203 Day 4 – Building an Autonomous Multi-Agent System with Tool Calling and Agent Lo
204 Day 4 – Building a Multi-Model AI Platform 34 Calls Across GPT-5, Claude & Open
205 Day 5 – Finalizing Your Agentic Workflow and Becoming an AI Engineer
206 Day 5 – Building the Price-Is-Right Agent UI with Gradio and DealAgentFramework
207 Day 5 – Course Wrap-Up Your Journey to AI Engineer

APPENDIX – ARCHIVE – Original Week 1 – now replaced by new version
208 Day 1 – Cold Open Jumping Right into LLM Engineering
209 Day 1 – Setting Up Ollama for Local LLM Deployment on Windows and Mac
210 Day 1 – Unleashing the Power of Local LLMs Build Spanish Tutor Using Ollama
211 Day 1 – LLM Engineering Roadmap From Beginner to Master in 8 Weeks
212 Day 1 – Building LLM Applications Chatbots, RAG, and Agentic AI Projects
213 Day 1 – From Wall Street to AI Ed Donner’s Path to Becoming an LLM Engineer
214 Day 1 – Setting Up Your LLM Development Environment Tools and Best Practices
215 Day 1 – Mac Setup Guide Jupyter Lab and Conda for LLM Projects
216 Day 1 – Setting Up Anaconda for LLM Engineering Windows Installation Guide
217 Day 1 – Alternative Python Setup for LLM Projects Virtualenv vs. Anaconda Guide
218 Day 1- Setting Up OpenAI API for LLM Development Keys, Pricing & Best Practices
219 Day 1 – Creating a .env File for Storing API Keys Safely
220 Day 1- Instant Gratification Project Creating an AI-Powered Web Page Summarizer
221 Day 1 – Implementing Text Summarization Using OpenAI’s GPT-4 and Beautiful Soup
222 Day 1 – Wrapping Up Day 1 Key Takeaways and Next Steps in LLM Engineering
223 Day 2 – Mastering LLM Engineering Key Skills and Tools for AI Development
224 Day 2 – Understanding Frontier Models GPT, Claude, and Open Source LLMs
225 Day 2 – How to Use Ollama for Local LLM Inference Python Tutorial with Jupyter
226 Day 2 – Hands-On LLM Task Comparing OpenAI and Ollama for Text Summarization
227 Day 3 – Frontier AI Models Comparing GPT-4, Claude, Gemini, and LLAMA
228 Day 3 – Comparing Leading LLMs Strengths and Business Applications
229 Day 3 – Exploring GPT-4o vs O1 Preview Key Differences in Performance
230 Day 3 – Creativity and Coding Leveraging GPT-4o’s Canvas Feature
231 Day 3 – Claude 3.5’s Alignment and Artifact Creation A Deep Dive
232 Day 3 – AI Model Comparison Gemini vs Cohere for Whimsical and Analytical Tasks
233 Day 3 – Evaluating Meta AI and Perplexity Nuances of Model Outputs
234 Day 3 – LLM Leadership Challenge Evaluating AI Models Through Creative Prompts
235 Day 4 – Revealing the Leadership Winner A Fun LLM Challenge
236 Day 4 – Exploring the Journey of AI From Early Models to Transformers
237 Day 4 – Understanding LLM Parameters From GPT-1 to Trillion-Weight Models
238 Day 4 – GPT Tokenization Explained How Large Language Models Process Text Input
239 Day 4 – How Context Windows Impact AI Language Models Token Limits Explained
240 Day 4 – Navigating AI Model Costs API Pricing vs. Chat Interface Subscriptions
241 Day 4 – Comparing LLM Context Windows GPT-4 vs Claude vs Gemini 1.5 Flash
242 Day 4 – Wrapping Up Day 4 Key Takeaways and Practical Insights
243 Day 5 – Building AI-Powered Marketing Brochures with OpenAI API and Python
244 Day 5 – JupyterLab Tutorial Web Scraping for AI-Powered Company Brochures
245 Day 5 – Structured Outputs in LLMs Optimizing JSON Responses for AI Projects
246 Day 5 – Creating and Formatting Responses for Brochure Content
247 Day 5 – Final Adjustments Optimizing Markdown and Streaming in JupyterLab
248 Day 5 – Mastering Multi-Shot Prompting Enhancing LLM Reliability in AI Projects
249 Day 5 – Assignment Developing Your Customized LLM-Based Tutor
250 Day 5 – Wrapping Up Week 1 Achievements and Next Steps

APPENDIX – ARCHIVE – Original Week 2 – now replaced by new version
251 Day 1 – Mastering Multiple AI APIs OpenAI, Claude, and Gemini for LLM Engineers
252 Day 1 – Streaming AI Responses Implementing Real-Time LLM Output in Python
253 Day 1 – How to Create Adversarial AI Conversations Using OpenAI and Claude APIs
254 Day 1 – AI Tools Exploring Transformers & Frontier LLMs for Developers
255 Day 2 – Building AI UIs with Gradio Quick Prototyping for LLM Engineers
256 Day 2 – Gradio Tutorial Create Interactive AI Interfaces for OpenAI GPT Models
257 Day 2 – Implementing Streaming Responses with GPT and Claude in Gradio UI
258 Day 2 – Building a Multi-Model AI Chat Interface with Gradio GPT vs Claude
259 Day 2 – Building Advanced AI UIs From OpenAI API to Chat Interfaces with Gradio
260 Day 3 – Building AI Chatbots Mastering Gradio for Customer Support Assistants
261 Day 3 – Build a Conversational AI Chatbot with OpenAI & Gradio Step-by-Step
262 Day 3 – Enhancing Chatbots with Multi-Shot Prompting and Context Enrichment
263 Day 3 – Mastering AI Tools Empowering LLMs to Run Code on Your Machine
264 Day 4 – Using AI Tools with LLMs Enhancing Large Language Model Capabilities
265 Day 4 – Building an AI Airline Assistant Implementing Tools with OpenAI GPT-4
266 Day 4 – How to Equip LLMs with Custom Tools OpenAI Function Calling Tutorial
267 Day 4 – Mastering AI Tools Building Advanced LLM-Powered Assistants with APIs
268 Day 5 – Multimodal AI Assistants Integrating Image and Sound Generation
269 Day 5 – Multimodal AI Integrating DALL-E 3 Image Generation in JupyterLab
270 Day 5 – Build a Multimodal AI Agent Integrating Audio & Image Tools
271 Day 5 – How to Build a Multimodal AI Assistant Integrating Tools and Agents

APPENDIX – ARCHIVE – Original Week 3 – now replaced by new version
272 Day 1 – Hugging Face Tutorial Exploring Open-Source AI Models and Datasets
273 Day 1 – Exploring HuggingFace Hub Models, Datasets & Spaces for AI Developers
274 Day 1 – Intro to Google Colab Cloud Jupyter Notebooks for Machine Learning
275 Day 1 – Hugging Face Integration with Google Colab Secrets and API Keys Setup
276 Day 1 – Mastering Google Colab Run Open-Source AI Models with Hugging Face
277 Day 2 – Hugging Face Transformers Using Pipelines for AI Tasks in Python
278 Day 2 – Hugging Face Pipelines Simplifying AI Tasks with Transformers Library
279 Day 2 – Mastering HuggingFace Pipelines Efficient AI Inference for ML Tasks
280 Day 3 – Exploring Tokenizers in Open-Source AI Llama, Phi-2, Qwen, & Starcoder
281 Day 3 – Tokenization Techniques in AI Using AutoTokenizer with LLAMA 3.1 Model
282 Day 3 – Comparing Tokenizers Llama, PHI-3, and QWEN2 for Open-Source AI Models
283 Day 3 – Hugging Face Tokenizers Preparing for Advanced AI Text Generation
284 Day 4 – Hugging Face Model Class Running Inference on Open-Source AI Models
285 Day 4 – Hugging Face Transformers Loading & Quantizing LLMs with Bits & Bytes
286 Day 4 – Hugging Face Transformers Generating Jokes with Open-Source AI Models
287 Day 4 – Mastering Hugging Face Transformers Models, Pipelines, and Tokenizers
288 Day 5 – Combining Frontier & Open-Source Models for Audio-to-Text Summarization
289 Day 5 – Using Hugging Face & OpenAI for AI-Powered Meeting Minutes Generation
290 Day 5 – Build a Synthetic Test Data Generator Open-Source AI Model for Business

APPENDIX – ARCHIVE – Original Week 4 – now replaced by new version
291 Day 1 – How to Choose the Right LLM Comparing Open and Closed Source Models
292 Day 1 – Chinchilla Scaling Law Optimizing LLM Parameters and Training Data Size
293 Day 1 – Limitations of LLM Benchmarks Overfitting and Training Data Leakage
294 Day 1 – Evaluating Large Language Models 6 Next-Level Benchmarks Unveiled
295 Day 1 – HuggingFace OpenLLM Leaderboard Comparing Open-Source Language Models
296 Day 1 – Master LLM Leaderboards Comparing Open Source and Closed Source Models
297 Day 2 – Comparing LLMs Top 6 Leaderboards for Evaluating Language Models
298 Day 2 – Specialized LLM Leaderboards Finding the Best Model for Your Use Case
299 Day 2 – LLAMA vs GPT-4 Benchmarking Large Language Models for Code Generation
300 Day 2 – Human-Rated Language Models Understanding the LM Sys Chatbot Arena
301 Day 2 – Commercial Applications of Large Language Models From Law to Education
302 Day 2 – Comparing Frontier and Open-Source LLMs for Code Conversion Projects
303 Day 3 – Leveraging Frontier Models for High-Performance Code Generation in C++
304 Day 3 – Comparing Top LLMs for Code Generation GPT-4 vs Claude 3.5 Sonnet
305 Day 3 – Optimizing Python Code with Large Language Models GPT-4 vs Claude 3.5
306 Day 3 – Code Generation Pitfalls When Large Language Models Produce Errors
307 Day 3 – Blazing Fast Code Generation How Claude Outperforms Python by 13,000x
308 Day 3 – Building a Gradio UI for Code Generation with Large Language Models
309 Day 3 – Optimizing C++ Code Generation Comparing GPT and Claude Performance
310 Day 3 – Comparing GPT-4 and Claude for Code Generation Performance Benchmarks
311 Day 4 – Open Source LLMs for Code Generation Hugging Face Endpoints Explored
312 Day 4 – How to Use HuggingFace Inference Endpoints for Code Generation Models
313 Day 4 – Integrating Open-Source Models with Frontier LLMs for Code Generation
314 Day 4 – Comparing Code Generation GPT-4, Claude, and CodeQuen LLMs
315 Day 4 – Mastering Code Generation with LLMs Techniques and Model Selection
316 Day 5 – Evaluating LLM Performance Model-Centric vs Business-Centric Metrics
317 Day 5 – Mastering LLM Code Generation Advanced Challenges for Python Developers

APPENDIX – ARCHIVE – Original Week 5 – now replaced by new version
318 Day 1 – RAG Fundamentals Leveraging External Data to Improve LLM Responses
319 Day 1 – Building a DIY RAG System Implementing Retrieval-Augmented Generation
320 Day 1 – Understanding Vector Embeddings The Key to RAG and LLM Retrieval
321 Day 2 – Unveiling LangChain Simplify RAG Implementation for LLM Applications
322 Day 2 – LangChain Text Splitter Tutorial Optimizing Chunks for RAG Systems
323 Day 2 – Preparing for Vector Databases OpenAI Embeddings and Chroma in RAG
324 Day 3 – Mastering Vector Embeddings OpenAI and Chroma for LLM Engineering
325 Day 3 – Visualizing Embeddings Exploring Multi-Dimensional Space with t-SNE
326 Day 3 – Building RAG Pipelines From Vectors to Embeddings with LangChain
327 Day 4 – Implementing RAG Pipeline LLM, Retriever, and Memory in LangChain
328 Day 4 – Mastering Retrieval-Augmented Generation Hands-On LLM Integration
329 Day 4 – Master RAG Pipeline Building Efficient RAG Systems
330 Day 5 – Optimizing RAG Systems Troubleshooting and Fixing Common Problems
331 Day 5 – Switching Vector Stores FAISS vs Chroma in LangChain RAG Pipelines
332 Day 5 – Demystifying LangChain Behind-the-Scenes of RAG Pipeline Construction
333 Day 5 – Debugging RAG Optimizing Context Retrieval in LangChain
334 Day 5 – Build Your Personal AI Knowledge Worker RAG for Productivity Boost

APPENDIX – ARCHIVE – Original Week 6 – now replaced by new version
335 Day 1 – Fine-Tuning Large Language Models From Inference to Training
336 Day 1 – Finding and Crafting Datasets for LLM Fine-Tuning Sources & Techniques
337 Day 1 – Data Curation Techniques for Fine-Tuning LLMs on Product Descriptions
338 Day 1 – Optimizing Training Data Scrubbing Techniques for LLM Fine-Tuning
339 Day 1 – Evaluating LLM Performance Model-Centric vs Business-Centric Metrics
340 Day 2 – LLM Deployment Pipeline From Business Problem to Production Solution
341 Day 2 – Prompting, RAG, and Fine-Tuning When to Use Each Approach
342 Day 2 – Productionizing LLMs Best Practices for Deploying AI Models at Scale
343 Day 2 – Optimizing Large Datasets for Model Training Data Curation Strategies
344 Day 2 – How to Create a Balanced Dataset for LLM Training Curation Techniques
345 Day 2 – Finalizing Dataset Curation Analyzing Price-Description Correlations
346 Day 2 – How to Create and Upload a High-Quality Dataset on HuggingFace
347 Day 3 – Feature Engineering and Bag of Words Building ML Baselines for NLP
348 Day 3 – Baseline Models in ML Implementing Simple Prediction Functions
349 Day 3 Feature Engineering Techniques for Amazon Product Price Prediction Models
350 Day 3 – Optimizing LLM Performance Advanced Feature Engineering Strategies
351 Day 3 – Linear Regression for LLM Fine-Tuning Baseline Model Comparison
352 Day 3 – Bag of Words NLP Implementing Count Vectorizer for Text Analysis in ML
353 Day 3 – Support Vector Regression vs Random Forest Machine Learning Face-Off
354 Day 3 – Comparing Traditional ML Models From Random to Random Forest
355 Day 4 – Evaluating Frontier Models Comparing Performance to Baseline Frameworks
356 Day 4 – Human vs AI Evaluating Price Prediction Performance in Frontier Models
357 Day 4 – GPT-4o Mini Frontier AI Model Evaluation for Price Estimation Tasks
358 Day 4 – Comparing GPT-4 and Claude Model Performance in Price Prediction Tasks
359 Day 4 – Frontier AI Capabilities LLMs Outperforming Traditional ML Models
360 Day 5 – Fine-Tuning LLMs with OpenAI Preparing Data, Training, and Evaluation
361 Day 5 – How to Prepare JSONL Files for Fine-Tuning Large Language Models (LLMs)
362 Day 5 – Step-by-Step Guide Launching GPT Fine-Tuning Jobs with OpenAI API
363 Day 5 – Fine-Tuning LLMs Track Training Loss & Progress with Weights & Biases
364 Day 5 – Evaluating Fine-Tuned LLMs Metrics Analyzing Training & Validation Loss
365 Day 5 – LLM Fine-Tuning Challenges When Model Performance Doesn’t Improve
366 Day 5 – Fine-Tuning Frontier LLMs Challenges & Best Practices for Optimization

APPENDIX – ARCHIVE – Original Week 7 – now replaced by new version
367 Day 1 – Mastering Parameter-Efficient Fine-Tuning LoRa, QLoRA & Hyperparameters
368 Day 1 – Introduction to LoRA Adaptors Low-Rank Adaptation Explained
369 Day 1 – QLoRA Quantization for Efficient Fine-Tuning of Large Language Models
370 Day 1 – Optimizing LLMs R, Alpha, and Target Modules in QLoRA Fine-Tuning
371 Day 1 – Parameter-Efficient Fine-Tuning PEFT for LLMs with Hugging Face
372 Day 1 – How to Quantize LLMs Reducing Model Size with 8-bit Precision
373 Day 1 Double Quantization & NF4 Advanced Techniques for 4-Bit LLM Optimization
374 Day 1 – Exploring PEFT Models The Role of LoRA Adapters in LLM Fine-Tuning
375 Day 1 – Model Size Summary Comparing Quantized and Fine-Tuned Models
376 Day 2 – How to Choose the Best Base Model for Fine-Tuning Large Language Models
377 Day 2 – Selecting the Best Base Model Analyzing HuggingFace’s LLM Leaderboard
378 Day 2 – Exploring Tokenizers Comparing LLAMA, QWEN, and Other LLM Models
379 Day 2 – Optimizing LLM Performance Loading and Tokenizing Llama 3.1 Base Model
380 Day 2 – Quantization Impact on LLMs Analyzing Performance Metrics and Errors
381 Day 2 – Comparing LLMs GPT-4 vs LLAMA 3.1 in Parameter-Efficient Tuning
382 Day 3 – QLoRA Hyperparameters Mastering Fine-Tuning for Large Language Models
383 Day 3 – Understanding Epochs and Batch Sizes in Model Training
384 Day 3 – Learning Rate, Gradient Accumulation, and Optimizers Explained
385 Day 3 – Setting Up the Training Process for Fine-Tuning
386 Day 3 – Configuring SFTTrainer for 4-Bit Quantized LoRA Fine-Tuning of LLMs
387 Day 3 – Fine-Tuning LLMs Launching the Training Process with QLoRA
388 Day 3 – Monitoring and Managing Training with Weights & Biases
389 Day 4 – Keeping Training Costs Low Efficient Fine-Tuning Strategies
390 Day 4 – Efficient Fine-Tuning Using Smaller Datasets for QLoRA Training
391 Day 4 – Visualizing LLM Fine-Tuning Progress with Weights and Biases Charts
392 Day 4 – Advanced Weights & Biases Tools and Model Saving on Hugging Face
393 Day 4 – End-to-End LLM Fine-Tuning From Problem Definition to Trained Model
394 Day 5 – The Four Steps in LLM Training From Forward Pass to Optimization
395 Day 5 – QLoRA Training Process Forward Pass, Backward Pass and Loss Calculation
396 Day 5 – Understanding Softmax and Cross-Entropy Loss in Model Training
397 Day 5 – Monitoring Fine-Tuning Weights & Biases for LLM Training Analysis
398 Day 5 – Revisiting the Podium Comparing Model Performance Metrics
399 Day 5 – Evaluation of our Proprietary, Fine-Tuned LLM against Business Metrics
400 Day 5 – Visualization of Results Did We Beat GPT-4
401 Day 5 – Hyperparameter Tuning for LLMs Improving Model Accuracy with PEFT

APPENDIX – ARCHIVE – Original Week 8 – now replaced by new version
402 Day 1 – From Fine-Tuning to Multi-Agent Systems Next-Level LLM Engineering
403 Day 1 Building a Multi-Agent AI Architecture for Automated Deal Finding Systems
404 Day 1 – Unveiling Modal Deploying Serverless Models to the Cloud
405 Day 1 – LLAMA on the Cloud Running Large Models Efficiently
406 Day 1 – Building a Serverless AI Pricing API Step-by-Step Guide with Modal
407 Day 1 – Multiple Production Models Ahead Preparing for Advanced RAG Solutions
408 Day 2 – Implementing Agentic Workflows Frontier Models and Vector Stores in RAG
409 Day 2 – Building a Massive Chroma Vector Datastore for Advanced RAG Pipelines
410 Day 2 – Visualizing Vector Spaces Advanced RAG Techniques for Data Exploration
411 Day 2 – 3D Visualization Techniques for RAG Exploring Vector Embeddings
412 Day 2 – Finding Similar Products Building a RAG Pipeline without LangChain
413 Day 2 – RAG Pipeline Implementation Enhancing LLMs with Retrieval Techniques
414 Day 2 – Random Forest Regression Using Transformers & ML for Price Prediction
415 Day 2 – Building an Ensemble Model Combining LLM, RAG, and Random Forest
416 Day 2 – Wrap-Up Finalizing Multi-Agent Systems and RAG Integration
417 Day 3 – Enhancing AI Agents with Structured Outputs Pydantic & BaseModel Guide
418 Day 3 – Scraping RSS Feeds Building an AI-Powered Deal Selection System
419 Day 3 – Structured Outputs in AI Implementing GPT-4 for Detailed Deal Selection
420 Day 3 – Optimizing AI Workflows Refining Prompts for Accurate Price Recognition
421 Day 3 – Mastering Autonomous Agents Designing Multi-Agent AI Workflows
422 Day 4 – The 5 Hallmarks of Agentic AI Autonomy, Planning, and Memory
423 Day 4 – Building an Agentic AI System Integrating Pushover for Notifications
424 Day 4 Implementing Agentic AI Creating a Planning Agent for Automated Workflows
425 Day 4 – Building an Agent Framework Connecting LLMs and Python Code
426 Day 4 – Completing Agentic Workflows Scaling for Business Applications
427 Day 5 – Autonomous AI Agents Building Intelligent Systems Without Human Input
428 Day 5 – AI Agents with Gradio Advanced UI Techniques for Autonomous Systems
429 Day 5 – Finalizing the Gradio UI for Our Agentic AI Solution
430 Day 5 Enhancing AI Agent UI Gradio Integration for Real-Time Log Visualization
431 Day 5 – Analyzing Results Monitoring Agent Framework Performance
432 Day 5 – AI Project Retrospective 8-Week Journey to Becoming an LLM Engineer