SKU/Artículo: AMZ-B0FMQC6PHC
Building a Small Language Model From Scratch: A Practical Guide to Designing, Training, and Deploying Efficient Language Models With Modern Tools (Series on Small Language Models)
Format:
Kindle
Detalles del producto
Disponibilidad:
Fuera de stock
Fuera de stock
Peso con empaque:
0.15 kg
0.15 kg
Devolución:
Sí
Sí
Condición
Nuevo
Nuevo
Producto de:
Amazon
Amazon
Viaja desde
USA
USA
Sobre este producto
- Unlock the full potential of transformer-based language models—without a supercomputer.Whether you're an AI enthusiast, indie developer, or machine learning engineer looking to go deeper, this book is your complete hands-on guide to building a small but powerful language model from the ground up. Designed for readers who want real, working code, not abstract theory, this is the definitive roadmap to understanding, training, and deploying efficient transformer models ranging from 10M to 100M parameters—all on consumer-grade GPUs or affordable cloud runtimes.You won’t just read about it—you’ll build it.Inside, you’ll create your own tokenizer, write and train your own GPT-style model from scratch using PyTorch and Hugging Face, finetune it for specific tasks, quantize it for faster inference, and serve it via an API—all while understanding every component in detail.What you'll learn and build:Understand what makes a model “small” and why it matters todayTokenization, attention, causal masking, and autoregression—demystifiedTrain a 10M–50M parameter transformer using real datasets and loggingEvaluate outputs using perplexity, sampling, and decoding techniquesFinetune your SLM with LoRA or PEFT for chatbots, code, or domain-specific tasksQuantize models to 8-bit or 4-bit using bitsandbytes, GPTQ, or AWQDeploy your model via FastAPI, Docker, or on edge devices like Raspberry PiScale up to 1B+ or shrink further into micro-model territory—confidentlyEach chapter combines deeply practical walkthroughs, expert insights, and fully executable scripts with a consistent project directory (slm-from-scratch/) you can extend and reuse.Whether you're building your own assistant, teaching students how transformers work, or just curious about the nuts and bolts of LLMs—this book empowers you to train smarter, deploy faster, and learn deeper.
Producto prohibido
Este producto no está disponible
Este producto viaja
de USA ![]()
a tus manos en
![]()
a tus manos en
Compra protegida
Disfruta de una experiencia de compra segura y confiable
Tarjetas de Crédito y Débito
Visa
Mastercard
American Express
Pagos a través de PayPal
Compra procesada en dólares con dinero en cuenta o tarjetas internacionales.
Paypal
Pagos a través de MODO
Compra procesada en pesos desde la App de tu banco.
PayPal
Tienes garantía de entrega 