{"product_id":"139888","title":"Today's AI development is SLM: Small and fast AI, completely conquering small language models. ","description":"\u003ccenter\u003e\u003cdiv style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/tmgdisk01.cafe24.com\/images\/vs\/4172\/sv\/3jXOZ3TsR3iOP9KsQutqmhHHRiWp9S.png?v=1765076960\" style=\"max-width:100%;max-height:10px\"\u003e\u003c\/div\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\n\n\u003cdiv style=\"width:95%\"\u003e\n\n \u003cdiv style=\"text-align:center;font-size:30px;font-weight:bolder;line-height:1.6em\"\u003eToday's AI development is SLM: Small, fast AI, mastering small language models. \u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"border-bottom:1px;border-bottom-style:dotted;border-color:;padding-bottom:20px\"\u003e\u003ccenter\u003e\u003ctable align=\"center\" width=\"100%\"\u003e\u003ctbody style=\"border:0px\"\u003e\n\n\u003ctr\u003e\u003ctd align=\"center\" style=\"line-height:1.2em;text-align:center;font-size:18px;color:black;font-weight:bold;padding-bottom:20px;\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\u003ctr\u003e\u003ctd style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/image.yes24.com\/goods\/152560033\/XL\" style=\"max-width:100%;height:auto\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/center\u003e\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;{split_style6}padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e Description \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;word-break:break-all;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eBook Introduction\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cdiv\u003e\u003cdiv\u003e Today's AI development is SLM: Small, fast AI, mastering small language models.\u003cbr\u003e Subtitle: From fine-tuning to RAG and distribution, I create a small but powerful AI with my own hands.\u003cbr\u003e\u003cbr\u003e Why Small Language Models (SLMs) Now?\u003cbr\u003e\u003cbr\u003e Large Language Models (LLMs) have taken artificial intelligence to the next level, but many developers and businesses have found them limited by high costs, slow speeds, and complex infrastructure.\u003cbr\u003e Now, the new protagonist in AI development is SLM (Small Language Model).\u003cbr\u003e\u003cbr\u003e SLM is small, fast, efficient, and can run anywhere: local, cloud, or edge.\u003cbr\u003e\n\n\u003c\/div\u003e\u003c\/div\u003e\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eindex\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e Today's AI development is SLM: Small, fast AI, mastering small language models.\u003cbr\u003e Preface to the book: Why Small Language Models (SLMs) Now?\u003cbr\u003e Part 1: SLM, the Beginning of a New Era\u003cbr\u003e Chapter 1: The Era of Large Language Models (LLMs) and the Emergence of SLMs\u003cbr\u003e 1.1. \u003cbr\u003eThe LLM That Changed the World: ChatGPT, GPT-4, and Beyond\u003cbr\u003e 1.2. The Shadow of LLM: High Costs, Slow Reasoning, and Difficulty in Control\u003cbr\u003e 1.3.\u003cbr\u003e The Rise of Alternatives: What is the Small Language Model (SLM)?\u003cbr\u003e 1.4. LLM vs. SLM: What, When, and How to Choose?\u003cbr\u003e 1.5.\u003cbr\u003e A look at representative SLM models\u003cbr\u003e Chapter 2: How SLM Works: How Does It Differ from LLM?\u003cbr\u003e 2.1.\u003cbr\u003e Revisiting the Core Principles of Transformer Architecture\u003cbr\u003e 2.2.\u003cbr\u003e The Art of Making Small: Innovations in Model Architecture\u003cbr\u003e 2.3.\u003cbr\u003e Efficient Learning: The Importance of High-Quality Data\u003cbr\u003e 2.4.\u003cbr\u003e Tokens, Embeddings, and Attention: Understanding the Internals of SLM\u003cbr\u003e Part 2: Hands-on with SLM (Basic Usage)\u003cbr\u003e Chapter 3: My First SLM: Setting Up the Development Environment\u003cbr\u003e 3.1.\u003cbr\u003e Required materials: Python, Jupyter Notebook\/VS Code\u003cbr\u003e 3.2.\u003cbr\u003e Install core libraries: PyTorch, Transformers, and Accelerate\u003cbr\u003e 3.3. CUDA Settings for GPU Usage (NVIDIA GPU Users)\u003cbr\u003e 3.4.\u003cbr\u003e Get started easily with a cloud\/Colab environment.\u003cbr\u003e 3.5. \u003cbr\u003e[Hands-on] \"Hello, SLM!\" - Loading the Model and Generating Your First Text\u003cbr\u003e Chapter 4: Mastering the Hugging Face and SLM Ecosystem\u003cbr\u003e 4.1.\u003cbr\u003e Hugging Face: A Playground for AI Developers\u003cbr\u003e 4.2.\u003cbr\u003e Model Hub: Find and compare the SLM models you want.\u003cbr\u003e 4.3.\u003cbr\u003e Datasets: Exploring Datasets for Fine-Tuning\u003cbr\u003e 4.4.\u003cbr\u003e The core of the Transformers library: how to use pipelines\u003cbr\u003e 4.5.\u003cbr\u003e [Practice] Creating a Text Summarization and Question-Answering Bot in Just 5 Lines with Pipeline\u003cbr\u003e Part 3: Building Your Own SLM Model (Tuning)\u003cbr\u003e Chapter 5: Fine-Tuning: Injecting My Data into SLM\u003cbr\u003e 5.1.\u003cbr\u003e What is fine tuning? Why is it necessary? (General purpose vs. specialized models)\u003cbr\u003e 5.2.\u003cbr\u003e Data Preparation: Creating a High-Quality Instruction Dataset\u003cbr\u003e 5.3.\u003cbr\u003e Full Fine-tuning: A powerful but heavy method\u003cbr\u003e 5.4.\u003cbr\u003e [Practice] Create Your Own Chatbot that Imitates Specific Speech Tone (Full Fine-Tuning)\u003cbr\u003e Chapter 6: Smart Tuning with the Lightweight Tuning Technique (PEFT)\u003cbr\u003e 6.1. The Need for Parameter-Efficient Fine-Tuning (PEFT)\u003cbr\u003e 6.2. \u003cbr\u003eLoRA (Low-Rank Adaptation): The most popular lightweight tuning technique\u003cbr\u003e 6.3.\u003cbr\u003e Easily Understand How LoRA Works\u003cbr\u003e 6.4.\u003cbr\u003e [Hands-on] Fine-tuning a low-spec GPU using LoRA\u003cbr\u003e 6.5. QLoRA: Tuning with Lower Memory\u003cbr\u003e Chapter 7: Model Quantization: Making It Lighter and Faster\u003cbr\u003e 7.1.\u003cbr\u003e What is Quantization? (FP16, INT8, INT4)\u003cbr\u003e 7.2.\u003cbr\u003e Why Quantization?: Saving Memory and Speeding Up Inference\u003cbr\u003e 7.3.\u003cbr\u003e Quantized loading using the bitsandbytes library\u003cbr\u003e 7.4.\u003cbr\u003e [Practice] Loading SLM with 4-bit quantization and comparing resource usage.\u003cbr\u003e Part 4: SLM, Practical Application Development and Deployment\u003cbr\u003e Chapter 8: Synergy Between RAG (Research Augmentation Generation) and SLM\u003cbr\u003e 8.1.\u003cbr\u003e Limitations of Language Models: Hallucinations and Lack of Up-to-Date Information\u003cbr\u003e 8.2. What is Retrieval-Augmented Generation (RAG)?\u003cbr\u003e 8.3.\u003cbr\u003e The Role of Vector DBs and Embedding Models (feat. FAISS, ChromaDB)\u003cbr\u003e 8.4.\u003cbr\u003e [Hands-on] Creating a Document-Based Q\u0026amp;A Chatbot by Combining SLM and RAG\u003cbr\u003e Chapter 9: SLM Application Deployment Strategies\u003cbr\u003e 9.1. \u003cbr\u003eOptimal Strategy for Each Deployment Scenario\u003cbr\u003e 9.2.\u003cbr\u003e Local\/On-Premises Deployment: Leveraging Ollama and vLLM\u003cbr\u003e 9.3.\u003cbr\u003e Cloud Server Deployment: Building Your Own API Server with FastAPI\u003cbr\u003e 9.4.\u003cbr\u003e Edge Device Deployment: Introducing Llama.cpp and the MLX Framework\u003cbr\u003e 9.5.\u003cbr\u003e [Practice] Serving a Fine-Tuned Model as an API Using FastAPI\u003cbr\u003e Chapter 10: Responsible Use of SLM and Future Prospects\u003cbr\u003e 10.1 AI Ethics: Issues of Bias, Fairness, and Transparency\u003cbr\u003e 10.2. SLM and Data Privacy\u003cbr\u003e 10.3. The Future of SLM: Smaller, Smarter, and More Multimodal\u003cbr\u003e 10.4.\u003cbr\u003e Growing with the open source community\u003cbr\u003e supplement\u003cbr\u003e Appendix A: Glossary of Terms\u003cbr\u003e Appendix B: List of Useful Tools and Libraries\u003cbr\u003e Appendix C: Situation-Specific Recommended SLM Models\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003ePublisher's Review\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e Low cost: Operating costs are dozens of times lower than those of an LLM.\u003cbr\u003e High-speed response: Fast inference speed suitable for real-time services.\u003cbr\u003e Enhanced security: Runs on local and intranet networks without data leakage.\u003cbr\u003e \u003cbr\u003eCustom optimization: Create AI tailored to specific domains, speech patterns, and business processes.\u003cbr\u003e\u003cbr\u003e Developers around the world are already leveraging SLM in a variety of areas, including customer service chatbots, on-device assistants, industrial data analytics, and real-time voice assistants.\u003cbr\u003e An era has begun where we can create “the AI ​​I want, in the environment I want,” without the need for large-scale computational resources.\u003cbr\u003e\u003cbr\u003e This book guides you step-by-step through implementing SLM from start to finish, from the basic concepts to the latest practices, fine-tuning, lightweighting, RAG combination, and deployment in various environments.\u003cbr\u003e Beyond simply following code, we've designed it to help you develop practical skills that allow you to design and optimize your own code. \u003cbr\u003e\n\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e GOODS SPECIFICS \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eDate of issue:\u003c\/strong\u003e August 19, 2025\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003ePage count, weight, size:\u003c\/strong\u003e 157 pages | 188*257*20mm\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eISBN13:\u003c\/strong\u003e 9791199401488\u003c\/div\u003e\n\n \u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e- \u003cstrong\u003eISBN10:\u003c\/strong\u003e 119940148X \u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cspan\u003e\u003c\/span\u003e\n\n\u003c\/center\u003e\n\n\n\u003c\/center\u003e","brand":"LIBRAIRIE COREENNE","offers":[{"title":"Default Title","offer_id":43893382905898,"sku":"139888","price":33.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0683\/2750\/5962\/files\/904bc2c3c288be5151cbdcfcda434f0d.jpg?v=1765399451","url":"https:\/\/librairie.coreenne.fr\/en\/products\/139888","provider":"LIBRAIRIE COREENNE","version":"1.0","type":"link"}