LLM Prompt Engineering for Developers The Art and Science of Unlocking LLMs' True Potential
"Explore the dynamic field of LLM prompt engineering with this book. Starting with fundamental NLP principles & progressing to sophisticated prompt engineering methods, this book serves as the perfect comprehensive guide. Key Features In-depth coverage of prompt engineering from basics to a...
| Otros Autores: | |
|---|---|
| Formato: | Libro electrónico |
| Idioma: | Inglés |
| Publicado: |
Birmingham :
Packt Publishing, Limited
2024.
|
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009825887106719 |
Tabla de Contenidos:
- Intro
- Preface
- What Are You Going to Learn?
- To Whom is This Guide For?
- Join the Community
- About the Author
- The Companion Toolkit
- Your Feedback Matters
- From NLP to Large Language Models
- What is Natural Language Processing?
- Language Models
- Statistical Models (N-Grams)
- Knowledge-Based Models
- Contextual Language Models
- Neural Network-Based Models
- Feedforward Neural Networks
- Recurrent Neural Networks (RNNs)
- Long Short-Term Memory (LSTM)
- Gated Recurrent Units (Grus)
- Transformer Models
- Bidirectional Encoder Representations from Transformers (BERT)
- Generative pre-trained transformer (GPT)
- What's Next?
- Introduction to Prompt Engineering
- OpenAI GPT and Prompting: An Introduction
- Generative Pre-trained Transformers (GPT) Models
- What Is GPT and How Is It Different from ChatGPT?
- The GPT models series: a closer look
- GPT-3.5
- GPT-4
- Other Models
- API Usage vs. Web Interface
- Tokens
- Costs, Tokens, and Initial Prompts: How to Calculate the Cost of Using a Model
- Prompting: How Does It Work?
- Probability and Sampling: At the Heart of GPT
- Understanding the API Parameters
- Temperature
- Top-p
- Top-k
- Sequence Length (max_tokens)
- Presence Penalty (presence_penalty)
- Frequency Penalty (frequency_penalty)
- Number of Responses (n)
- Best of (best_of)
- OpenAI Official Examples
- Using the API without Coding
- Completion (Deprecated)
- Chat
- Insert (Deprecated)
- Edit (Deprecated)
- Setting Up the Environment
- Choosing the Model
- Choosing the Programming Language
- Installing the Prerequisites
- Installing the OpenAI Python library
- Getting an OpenAI API key
- A Hello World Example
- Interactive Prompting
- Interactive Prompting with Multiline Prompt
- Few-Shot Learning and Chain of Thought
- What Is Few-Shot Learning?
- Zero-Shot vs Few-Shot Learning
- Approaches to Few-Shot Learning
- Prior Knowledge about Similarity
- Prior Knowledge about Learning
- Prior Knowledge of Data
- Examples of Few-Shot Learning
- Limitations of Few-Shot Learning
- Chain of Thought (CoT)
- Zero-Shot CoT Prompting
- Auto Chain of Thought Prompting (AutoCoT)
- Self-Consistency
- Transfer Learning
- What Is Transfer Learning?
- Inductive Transfer
- Transductive Transfer
- Inductive vs. Transductive Transfer
- Transfer Learning, Fine-Tuning, and Prompt Engineering
- Fine-Tuning with a Prompt Dataset: A Practical Example
- Why Is Prompt Engineering Vital for Transfer Learning and Fine-Tuning?
- Perplexity as a Metric for Prompt Optimization
- Avoid Surprising the Model
- How to Calculate Perplexity?
- A Practical Example with Betterprompt
- Hack the Prompt
- ReAct: Reason + Act
- What Is It?
- React Using Lanchain
- General Knowledge Prompting
- What Is General Knowledge Prompting?
- Example of General Knowledge Prompting
