book

Hands-On Large Language Models

by Jay Alammar, Maarten Grootendorst

September 2024

Beginner to intermediate

428 pages

10h 29m

English

O'Reilly Media, Inc.

Audio summary available

Read now

Unlock full access

Includes

Quizzes

Preface
An Intuition-First PhilosophyPrerequisitesBook StructurePart I: Understanding Language ModelsPart II: Using Pretrained Language ModelsPart III: Training and Fine-Tuning Language ModelsHardware and Software RequirementsAPI KeysConventions Used in This BookUsing Code ExamplesO’Reilly Online LearningHow to Contact UsAcknowledgments
I. Understanding Language Models
1. An Introduction to Large Language Models
What Is Language AI?A Recent History of Language AIRepresenting Language as a Bag-of-WordsBetter Representations with Dense Vector EmbeddingsTypes of EmbeddingsEncoding and Decoding Context with AttentionAttention Is All You NeedRepresentation Models: Encoder-Only ModelsGenerative Models: Decoder-Only ModelsThe Year of Generative AIThe Moving Definition of a “Large Language Model”The Training Paradigm of Large Language ModelsLarge Language Model Applications: What Makes Them So Useful?Responsible LLM Development and UsageLimited Resources Are All You NeedInterfacing with Large Language ModelsProprietary, Private ModelsOpen ModelsOpen Source FrameworksGenerating Your First TextSummary
2. Tokens and Embeddings
LLM TokenizationHow Tokenizers Prepare the Inputs to the Language ModelDownloading and Running an LLMHow Does the Tokenizer Break Down Text?Word Versus Subword Versus Character Versus Byte TokensComparing Trained LLM TokenizersTokenizer PropertiesToken EmbeddingsA Language Model Holds Embeddings for the Vocabulary of Its TokenizerCreating Contextualized Word Embeddings with Language ModelsText Embeddings (for Sentences and Whole Documents)Word Embeddings Beyond LLMsUsing pretrained Word EmbeddingsThe Word2vec Algorithm and Contrastive TrainingEmbeddings for Recommendation SystemsRecommending Songs by EmbeddingsTraining a Song Embedding ModelSummary
3. Looking Inside Large Language Models
An Overview of Transformer ModelsThe Inputs and Outputs of a Trained Transformer LLMThe Components of the Forward PassChoosing a Single Token from the Probability Distribution (Sampling/Decoding)Parallel Token Processing and Context SizeSpeeding Up Generation by Caching Keys and ValuesInside the Transformer BlockRecent Improvements to the Transformer ArchitectureMore Efficient AttentionThe Transformer BlockPositional Embeddings (RoPE)Other Architectural Experiments and ImprovementsSummary
II. Using Pretrained Language Models
4. Text Classification
The Sentiment of Movie ReviewsText Classification with Representation ModelsModel SelectionUsing a Task-Specific ModelClassification Tasks That Leverage EmbeddingsSupervised ClassificationWhat If We Do Not Have Labeled Data?Text Classification with Generative ModelsUsing the Text-to-Text Transfer TransformerChatGPT for ClassificationSummary
5. Text Clustering and Topic Modeling
ArXiv’s Articles: Computation and LanguageA Common Pipeline for Text ClusteringEmbedding DocumentsReducing the Dimensionality of EmbeddingsCluster the Reduced EmbeddingsInspecting the ClustersFrom Text Clustering to Topic ModelingBERTopic: A Modular Topic Modeling FrameworkAdding a Special Lego BlockThe Text Generation Lego BlockSummary
6. Prompt Engineering
Using Text Generation ModelsChoosing a Text Generation ModelLoading a Text Generation ModelControlling Model OutputIntro to Prompt EngineeringThe Basic Ingredients of a PromptInstruction-Based PromptingAdvanced Prompt EngineeringThe Potential Complexity of a PromptIn-Context Learning: Providing ExamplesChain Prompting: Breaking up the ProblemReasoning with Generative ModelsChain-of-Thought: Think Before AnsweringSelf-Consistency: Sampling OutputsTree-of-Thought: Exploring Intermediate StepsOutput VerificationProviding ExamplesGrammar: Constrained SamplingSummary
7. Advanced Text Generation Techniques and Tools
Model I/O: Loading Quantized Models with LangChainChains: Extending the Capabilities of LLMsA Single Link in the Chain: Prompt TemplateA Chain with Multiple PromptsMemory: Helping LLMs to Remember ConversationsConversation BufferWindowed Conversation BufferConversation SummaryAgents: Creating a System of LLMsThe Driving Power Behind Agents: Step-by-step ReasoningReAct in LangChainSummary

8. Semantic Search and Retrieval-Augmented Generation
Overview of Semantic Search and RAGSemantic Search with Language ModelsDense RetrievalRerankingRetrieval Evaluation MetricsRetrieval-Augmented Generation (RAG)From Search to RAGExample: Grounded Generation with an LLM APIExample: RAG with Local ModelsAdvanced RAG TechniquesRAG EvaluationSummary
9. Multimodal Large Language Models
Transformers for VisionMultimodal Embedding ModelsCLIP: Connecting Text and ImagesHow Can CLIP Generate Multimodal Embeddings?OpenCLIPMaking Text Generation Models MultimodalBLIP-2: Bridging the Modality GapPreprocessing Multimodal InputsUse Case 1: Image CaptioningUse Case 2: Multimodal Chat-Based PromptingSummary
III. Training and Fine-Tuning Language Models
10. Creating Text Embedding Models
Embedding ModelsWhat Is Contrastive Learning?SBERTCreating an Embedding ModelGenerating Contrastive ExamplesTrain ModelIn-Depth EvaluationLoss FunctionsFine-Tuning an Embedding ModelSupervisedAugmented SBERTUnsupervised LearningTransformer-Based Sequential Denoising Auto-EncoderUsing TSDAE for Domain AdaptationSummary
11. Fine-Tuning Representation Models for Classification
Supervised ClassificationFine-Tuning a Pretrained BERT ModelFreezing LayersFew-Shot ClassificationSetFit: Efficient Fine-Tuning with Few Training ExamplesFine-Tuning for Few-Shot ClassificationContinued Pretraining with Masked Language ModelingNamed-Entity RecognitionPreparing Data for Named-Entity RecognitionFine-Tuning for Named-Entity RecognitionSummary
12. Fine-Tuning Generation Models
The Three LLM Training Steps: Pretraining, Supervised Fine-Tuning, and Preference TuningSupervised Fine-Tuning (SFT)Full Fine-TuningParameter-Efficient Fine-Tuning (PEFT)Instruction Tuning with QLoRATemplating Instruction DataModel QuantizationLoRA ConfigurationTraining ConfigurationTrainingMerge WeightsEvaluating Generative ModelsWord-Level MetricsBenchmarksLeaderboardsAutomated EvaluationHuman EvaluationPreference-Tuning / Alignment / RLHFAutomating Preference Evaluation Using Reward ModelsThe Inputs and Outputs of a Reward ModelTraining a Reward ModelTraining No Reward ModelPreference Tuning with DPOTemplating Alignment DataModel QuantizationTraining ConfigurationTrainingSummary
Afterword
Index
About the Authors

Content preview from Hands-On Large Language Models

Chapter 9. Multimodal Large Language Models

When you think about large language models (LLMs), multimodality might not be the first thing that comes to mind. After all, they are language models! But we can quickly see that models can be much more useful if they’re able to handle types of data other than text. It’s very useful, for example, if a language model is able to glance at a picture and answer questions about it. A model that is able to handle text and images (each of which is called a modality) is said to be multimodal, as we can see in Figure 9-1.

We have seen all manner of emerging behaviors rising from LLMs, from generalization capabilities and reasoning to arithmetic and linguistics. As models grow larger and smarter, so do their skill sets.¹

The ability to receive and reason with multimodal input might further increase and help emerge capabilities that were previously locked. In practice, language does not solely live in a vacuum. As an example, your body language, facial expressions, intonation, etc. are all methods of communication that enhance the spoken word.

The same thing applies to LLMs; if we can enable ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Build a Large Language Model (From Scratch)

Publisher Resources

ISBN: 9781098150952Errata Page

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Hands-On Large Language Models

by Jay Alammar, Maarten Grootendorst

Chapter 9. Multimodal Large Language Models

Figure 9-1. Models that are able to deal with different types (or modalities) of data, such as images, audio, video, or sensors, are said to be multimodal. It’s possible for a model to accept a modality as input yet not be able to generate in that modality.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.