Engineering with Small Language Models: Efficient AI Design, Training, and Deployment for Developers - Brossura
Sinossi
Can efficient AI be powerful without requiring massive compute resources or costly cloud subscriptions?
Engineering with Small Language Models answers this question by showing how Small Language Models (SLMs) deliver high-performance natural language processing in resource-constrained environments. While large language models dominate headlines, SLMs offer a compelling alternative: fast inference, low memory usage, and flexible deployment on CPUs, mobile devices, edge hardware, and affordable GPUs. With tools like Hugging Face, PyTorch, and advanced techniques such as quantization and federated learning, you can build production-ready AI systems that are lightweight, secure, and scalable.
This comprehensive guide takes you through the entire SLM lifecycle, from design and training to optimization and deployment. Written for developers, AI engineers, and data scientists, it provides clear, practical workflows backed by real-world code and case studies. You’ll learn how to fine-tune models with parameter-efficient methods like LoRA, compress them using 4-bit quantization and pruning, and deploy them on devices like Raspberry Pi or smartphones. The book also addresses critical topics like privacy, bias mitigation, and compliance, ensuring your AI systems are ethical and production-ready.
What’s Inside:
- Setting up and running SLMs with Hugging Face and PyTorch
- Fine-tuning with LoRA, QLoRA, and adapters for domain-specific tasks
- Compression techniques: 4-bit/8-bit quantization, GPTQ, AWQ, and pruning
- Exporting models to ONNX, TensorFlow Lite, and Core ML for edge deployment
- On-device inference for Raspberry Pi, Android, iOS, and IoT devices
- Federated learning and differential privacy for secure, privacy-preserving AI
- Building scalable inference APIs with FastAPI and TorchServe
- Kubernetes, serverless, and autoscaling strategies for cloud deployment
- Ethical AI: bias mitigation, interpretability, and accessibility best practices
- Case studies in chatbots, healthcare, finance, and IoT
- CI/CD pipelines, monitoring, and performance optimization workflows
- Appendices with scripts, datasets, and troubleshooting guides
About the Reader: This book is for developers, AI engineers, data scientists, and advanced learners who want to build efficient, scalable NLP systems without relying on massive infrastructure. A working knowledge of Python and basic familiarity with machine learning concepts are all you need to get started. Whether you’re a startup founder integrating AI into a mobile app, a researcher optimizing models for edge devices, or an engineer deploying secure APIs, this book equips you with practical tools and insights.
SLMs are transforming AI by making it faster, lighter, and more accessible. From fine-tuning on a laptop to deploying on constrained IoT devices, Engineering with Small Language Models is your definitive resource for creating impactful AI solutions. Get your copy today and start building smarter, more efficient systems—one small model at a time.
Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
Risultati della ricerca per Engineering with Small Language Models: Efficient AI...
Foto dell'editore
Engineering with Small Language Models: Efficient AI Design, Training, and Deployment for Developers
Da: GreatBookPrices, Columbia, MD, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: As New. Unread book in perfect condition. Codice articolo 50961129
Compra usato
EUR 17,27
Spedizione EUR 2,24
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
Engineering with Small Language Models: Efficient AI Design, Training, and Deployment for Developers
Da: GreatBookPrices, Columbia, MD, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: New. Codice articolo 50961129-n
Compra nuovo
EUR 18,16
Spedizione EUR 2,24
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
Engineering with Small Language Models (Paperback)
Print on DemandDa: Grand Eagle Retail, Bensenville, IL, U.S.A.
Valutazione del venditore 5 su 5 stelle
Paperback. Condizione: new. Paperback. Can efficient AI be powerful without requiring massive compute resources or costly cloud subscriptions?Engineering with Small Language Models answers this question by showing how Small Language Models (SLMs) deliver high-performance natural language processing in resource-constrained environments. While large language models dominate headlines, SLMs offer a compelling alternative: fast inference, low memory usage, and flexible deployment on CPUs, mobile devices, edge hardware, and affordable GPUs. With tools like Hugging Face, PyTorch, and advanced techniques such as quantization and federated learning, you can build production-ready AI systems that are lightweight, secure, and scalable.This comprehensive guide takes you through the entire SLM lifecycle, from design and training to optimization and deployment. Written for developers, AI engineers, and data scientists, it provides clear, practical workflows backed by real-world code and case studies. You'll learn how to fine-tune models with parameter-efficient methods like LoRA, compress them using 4-bit quantization and pruning, and deploy them on devices like Raspberry Pi or smartphones. The book also addresses critical topics like privacy, bias mitigation, and compliance, ensuring your AI systems are ethical and production-ready.What's Inside: Setting up and running SLMs with Hugging Face and PyTorchFine-tuning with LoRA, QLoRA, and adapters for domain-specific tasksCompression techniques: 4-bit/8-bit quantization, GPTQ, AWQ, and pruningExporting models to ONNX, TensorFlow Lite, and Core ML for edge deploymentOn-device inference for Raspberry Pi, Android, iOS, and IoT devicesFederated learning and differential privacy for secure, privacy-preserving AIBuilding scalable inference APIs with FastAPI and TorchServeKubernetes, serverless, and autoscaling strategies for cloud deploymentEthical AI: bias mitigation, interpretability, and accessibility best practicesCase studies in chatbots, healthcare, finance, and IoTCI/CD pipelines, monitoring, and performance optimization workflowsAppendices with scripts, datasets, and troubleshooting guidesAbout the Reader: This book is for developers, AI engineers, data scientists, and advanced learners who want to build efficient, scalable NLP systems without relying on massive infrastructure. A working knowledge of Python and basic familiarity with machine learning concepts are all you need to get started. Whether you're a startup founder integrating AI into a mobile app, a researcher optimizing models for edge devices, or an engineer deploying secure APIs, this book equips you with practical tools and insights.SLMs are transforming AI by making it faster, lighter, and more accessible. From fine-tuning on a laptop to deploying on constrained IoT devices, Engineering with Small Language Models is your definitive resource for creating impactful AI solutions. Get your copy today and start building smarter, more efficient systems-one small model at a time. This item is printed on demand. Shipping may be from multiple locations in the US or from the UK, depending on stock availability. Codice articolo 9798298559843
Compra nuovo
EUR 20,46
Spedizione gratuita
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: 1 disponibili
Foto dell'editore
Engineering with Small Language Models
Print on DemandDa: PBShop.store UK, Fairford, GLOS, Regno Unito
Valutazione del venditore 5 su 5 stelle
PAP. Condizione: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000. Codice articolo L0-9798298559843
Compra nuovo
EUR 18,49
Spedizione EUR 4,81
Spedito da Regno Unito a U.S.A.
Spedito da Regno Unito a U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
Engineering with Small Language Models: Efficient AI Design, Training, and Deployment for Developers
Da: GreatBookPricesUK, Woodford Green, Regno Unito
Valutazione del venditore 5 su 5 stelle
Condizione: New. Codice articolo 50961129-n
Compra nuovo
EUR 18,48
Spedizione EUR 17,35
Spedito da Regno Unito a U.S.A.
Spedito da Regno Unito a U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
Engineering with Small Language Models: Efficient AI Design, Training, and Deployment for Developers
Da: GreatBookPricesUK, Woodford Green, Regno Unito
Valutazione del venditore 5 su 5 stelle
Condizione: As New. Unread book in perfect condition. Codice articolo 50961129
Compra usato
EUR 19,79
Spedizione EUR 17,35
Spedito da Regno Unito a U.S.A.
Spedito da Regno Unito a U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
Engineering with Small Language Models (Paperback)
Print on DemandDa: CitiRetail, Stevenage, Regno Unito
Valutazione del venditore 5 su 5 stelle
Paperback. Condizione: new. Paperback. Can efficient AI be powerful without requiring massive compute resources or costly cloud subscriptions?Engineering with Small Language Models answers this question by showing how Small Language Models (SLMs) deliver high-performance natural language processing in resource-constrained environments. While large language models dominate headlines, SLMs offer a compelling alternative: fast inference, low memory usage, and flexible deployment on CPUs, mobile devices, edge hardware, and affordable GPUs. With tools like Hugging Face, PyTorch, and advanced techniques such as quantization and federated learning, you can build production-ready AI systems that are lightweight, secure, and scalable.This comprehensive guide takes you through the entire SLM lifecycle, from design and training to optimization and deployment. Written for developers, AI engineers, and data scientists, it provides clear, practical workflows backed by real-world code and case studies. You'll learn how to fine-tune models with parameter-efficient methods like LoRA, compress them using 4-bit quantization and pruning, and deploy them on devices like Raspberry Pi or smartphones. The book also addresses critical topics like privacy, bias mitigation, and compliance, ensuring your AI systems are ethical and production-ready.What's Inside: Setting up and running SLMs with Hugging Face and PyTorchFine-tuning with LoRA, QLoRA, and adapters for domain-specific tasksCompression techniques: 4-bit/8-bit quantization, GPTQ, AWQ, and pruningExporting models to ONNX, TensorFlow Lite, and Core ML for edge deploymentOn-device inference for Raspberry Pi, Android, iOS, and IoT devicesFederated learning and differential privacy for secure, privacy-preserving AIBuilding scalable inference APIs with FastAPI and TorchServeKubernetes, serverless, and autoscaling strategies for cloud deploymentEthical AI: bias mitigation, interpretability, and accessibility best practicesCase studies in chatbots, healthcare, finance, and IoTCI/CD pipelines, monitoring, and performance optimization workflowsAppendices with scripts, datasets, and troubleshooting guidesAbout the Reader: This book is for developers, AI engineers, data scientists, and advanced learners who want to build efficient, scalable NLP systems without relying on massive infrastructure. A working knowledge of Python and basic familiarity with machine learning concepts are all you need to get started. Whether you're a startup founder integrating AI into a mobile app, a researcher optimizing models for edge devices, or an engineer deploying secure APIs, this book equips you with practical tools and insights.SLMs are transforming AI by making it faster, lighter, and more accessible. From fine-tuning on a laptop to deploying on constrained IoT devices, Engineering with Small Language Models is your definitive resource for creating impactful AI solutions. Get your copy today and start building smarter, more efficient systems-one small model at a time. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability. Codice articolo 9798298559843
Compra nuovo
EUR 22,62
Spedizione EUR 42,79
Spedito da Regno Unito a U.S.A.
Spedito da Regno Unito a U.S.A.
Quantità: 1 disponibili