Generative AI & Large Language Models (LLMs)

Introduction to LLMs

Unlock the potential of large language models. Build applications and understand their underlying mechanics for effective AI solutions.

1. Welcome and Course Overview
2. What is an LLM?
3. What makes an LLM Large?
4. Comparison of Old vs New Methods
1. LLM Use Cases
2. Next-Word Prediction
3. Mathematical Equation of Autoregression
1. How LLMs Work
2. The First Level of LLM Usage
3. The Second Level of LLM Usage
4. The Third Level of LLM Usage
1. What is an API?
2. Advantages of API Over Web
3. OpenAI API Models
4. Tokens
5. Getting Started
1. Obtaining Secret Key from OpenAl
2. Jupyter Notebook and API Setup
3. Next-Word Prediction Using API
4. Obtaining Multiple Outputs and Parameter Experimentation
1. Lessons From The Previous Module
2. What is HuggingFace?
3. Transformers Library
4. Transformers Library Capabilities
5. Specifying the Particular Model
6. HuggingFace Repository Walkthrough
7. Model Card Walkthrough
1. Notebook Setup and Pipeline Example
2. Sentiment Analysis Example
3. Batch Prediction
4. Multiple Targets
5. Text Summarization
6. Conversational Chatbot
1. What is Prompt Engineering?
2. The Two Levels of Prompt Engineering
3. Use Cases
4. Traditional and New Methods
5. The 7 Tricks of Prompt Engineering
1. Secret Key Setupt and Imports
2. Initializing Our Chatbot
3. Defining the Prompt Template
4. Utilizing Langchain
1. What is Fine-Tuning?
2. 3 Ways to Fine-Tune
3. Steps in Supervised Fine-tuning
4. Low Rank Adaptation (LoRA)
1. LLMs and World Knowledge
2. The 2 Key Limitations
3. Overview of the RAG Process
4. The RAG Module
5. The Knowledge Base