README.md

Large Language Model (LLM) Hands On

Reference Book: Mastering Large Language Models [Google Books Preview] [Github Link]
Code Explanation: Link

Contents

Rule-Based Models

• Phone Number Extraction Using Regular Expressions
• Pattern Matching Using Parts of Speech Tags
• Matching Specific Tokens with Specific Attributes

Statistical Language Models

• Simple Implementation of Bigram Language Model
• Ngrams of Sentence

Data Preprocessing

• Basic Data Cleaning
• Entity Detection
• Anonymization
• Text Pre-processing Example
• Parts-of-Speech (POS) tags
• Dependency Parsing

Neural Networks

• Feedforward Neural Network to Solve XNOR Problem
• LSTM for IMDB movie review sentiment classification
• GRU for IMDB movie review sentiment classification
• Bidirectional RNN for IMDB movie review sentiment classification
• CNN Based Language Model Architecture

Transformer-Based Models

• Self-attention Visualization
• Positional Encoding

Training Large Language Models

• Designing a Tiny LLM for Text Generation
• Designing a Character-level Text Generation Model
• Designing a Word-level Text Generation Model
• Designing a Word-level Text Generation Model with Large Dataset
• Text Generation Model Using T5

Fine-Tuning Large Language Models

• Fine-Tuning Gemma 2 2b-it Model From Hugging Face

Introduction to Ollama

• Inferencing Llama 3.2 Model Using Ollama Python Library
• Inferencing Gemma 2 Model Using Ollama Python Library
• Inferencing Llava Model Using Ollama Python Library

Introduction to Langchain

• Inferencing Llama 3.2 Model Using Langchain and Ollama
• Inferencing Llava Model Using Langchain and Ollama

Retrieval-Augmented Generation (RAG)

• Designing a Retrieval-Augmented Generation (RAG) Pipeline Using LlamaIndex and Ollama
• Designing a Retrieval-Augmented Generation (RAG) Pipeline for Gemma 2 Model

Prompt Engineering

• Types of Prompts