Iozzia G. - Domain-Specific Small Language Models [2026, PDF, ENG] torrent

Книги и журналы » Компьютерная литература » Программирование (книги)

Domain-Specific Small Language Models

Год издания: 2026
Автор: Iozzia G.

Издательство: Manning
ISBN: 978-1633436701
Язык: Английский

Формат: PDF
Качество: Издательский макет или текст (eBook)
Интерактивное оглавление: Да
Количество страниц: 376

Описание: Bigger isn’t always better. Train and tune highly focused language models optimized for domain specific tasks.
When you need a language model to respond accurately and quickly about a specific field of knowledge, the sprawling capacity of a LLM may hurt more than it helps. Domain-Specific Small Language Models teaches you to build generative AI models optimized for specific fields.
In Domain-Specific Small Language Models you’ll discover:
• Model sizing best practices
• Open source libraries, frameworks, utilities and runtimes
• Fine-tuning techniques for custom datasets
• Hugging Face’s libraries for SLMs
• Running SLMs on commodity hardware
• Model optimization or quantization
Perfect for cost- or hardware-constrained environments, Small Language Models (SLMs) train on domain specific data for high-quality results in specific tasks. In Domain-Specific Small Language Models you’ll develop SLMs that can generate everything from Python code to protein structures and antibody sequences—all on commodity hardware.
[spoiler="Примеры страниц (скриншоты)"]

[/spoiler]
[spoiler="Оглавление"]
Part 1 First steps 1
1. Small language models 3
Part 2 Core domain-specific LLMs 15
2. Tuning for a specific domain 17
3. End-to-end transformer fine-tuning 36
4. Running inference 51
5. Exploring ONNX 71
6. Quantizing for your production environment 96
Part 3 Real-world use cases 119
7. Generating Python code 121
8. Generating protein structures 145
Part 4 Advanced concepts 163
9. Advanced quantization techniques 165
10. Profiling insights 184
11. Deployment and serving 206
12. Running on your laptop 235
13. Creating end-to-end LLM applications 258
14. Advanced components for LLM applications 292
15. Test-time compute and small language models 326
[/spoiler]