null Book

Chapter 1: What Is Language AI?

Chapter 2: A Recent History of Language AI

Chapter 3: Representing Language as a Bag-of-Words

Chapter 4: Better Representations with Dense Vector Embeddings

Chapter 5: Encoding and Decoding Context with Attention

Chapter 6: Overview of Encoder-Only and Decoder-Only Models

Chapter 7: The Year of Generative AI and the Evolution of LLMs

Chapter 8: The Training Paradigm of LLMs and Responsible Development

Chapter 9: LLM Tokenization

Chapter 10: Tokenizer Comparisons: Word, Subword, Character, and Byte Tokens

Chapter 11: Token Embeddings and Contextualized Representations

Chapter 12: Pretrained Embeddings Beyond LLMs

Chapter 13: Applications in Recommendation Systems

Chapter 14: Anatomy of Transformer Models

Chapter 15: Components of the Forward Pass

Chapter 16: Caching Keys and Values for Efficient Token Generation

Chapter 17: Recent Improvements to Transformer Architectures

Chapter 18: Understanding Positional Embeddings and Advanced Experiments

Chapter 19: Sentiment Analysis and Supervised Classification

Chapter 20: Using Embeddings for Classification Tasks

Chapter 21: Leveraging Generative Models for Classification (e.g., ChatGPT)

Chapter 22: A Pipeline for Text Clustering

Chapter 23: Embedding, Dimensionality Reduction, and Clustering Techniques

Chapter 24: From Clustering to Topic Modeling with BERTopic Framework

Chapter 25: Introduction to Prompt Engineering

Chapter 26: Instruction-Based and Chain Prompting

Chapter 27: Advanced Techniques: Chain-of-Thought, Tree-of-Thought, and Output Verification

Chapter 28: Best Practices for Crafting Effective Prompts

Chapter 29: Loading Quantized Models with LangChain

Chapter 30: Building Chains and Agents for Complex Workflows

Chapter 31: Enhancing Conversational Memory with LangChain Tools

Chapter 32: Semantic Search Overview

Chapter 33: Dense Retrieval and Reranking Techniques

Chapter 34: Grounded Generation and Advanced RAG Implementations

Chapter 35: Evaluating RAG Performance

Chapter 36: Vision Transformers and Multimodal Embeddings

Chapter 37: CLIP and OpenCLIP for Connecting Text and Images

Chapter 38: Multimodal Use Cases: Image Captioning and Chat-Based Prompting

Chapter 39: Contrastive Learning and SBERT

Chapter 40: Techniques for Data Augmentation and Synthesis

Chapter 41: Training and Evaluating Embedding Models

Chapter 42: Supervised Fine-Tuning with Pretrained BERT

Chapter 43: Few-Shot Classification with SetFit

Chapter 44: Named-Entity Recognition (NER) and Data Preparation

Chapter 45: Three Steps of LLM Training: Pretraining, Supervised Fine-Tuning, and Preference Tuning

Chapter 46: Parameter-Efficient Fine-Tuning (PEFT) with QLoRA

Chapter 47: Techniques for Alignment: RLHF and DPO

Don't Miss Out!