{"product_id":"138210","title":"Practical LLM Fine Tuning in One Book ","description":"\u003ccenter\u003e\u003cdiv style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/tmgdisk01.cafe24.com\/images\/vs\/4172\/sv\/3jXPCfN54jqImZYUtXMKWP9JMfhexR.png?v=1765061243\" 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\"\u003e Practical LLM Fine Tuning in One Book \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\/140002006\/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\n\u003cdiv\u003e\u003cdiv\u003e \u003cb\u003eLet's learn the fine tuning, PEFT, and vLLM serving techniques that are essential in the field through hands-on practice!\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003eLearn everything about LLM Fine-Tuning from the forefront of AI technology! Master it step-by-step, from theoretical foundations to practical application. Covering the historical development of NLP and the core principles of backpropagation, an in-depth understanding of GPT models: from self-attention and tokenizer implementation to practical applications, analysis of the latest Gemma 2 and Llama 3 models and GPU parallel learning, hands-on fine-tuning techniques using LoRA and QLoRA, and model serving applicable to real-world services with vLLM.\u003cbr\u003e You can learn both theory and practice simultaneously through hands-on projects in the Runpod environment, and it provides know-how that can be immediately applied in real-world environments, from single GPUs to multi-GPU environments.\u003cbr\u003e\n\u003c\/div\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cul\u003e\u003cli\u003e You can preview some of the book's contents.\u003cbr\u003e \u003cspan\u003ePreview\u003c\/span\u003e\n\n\u003c\/li\u003e\u003c\/ul\u003e\u003c\/div\u003e\n\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 \u003cb\u003e▣ Chapter 1: NLP's Past and Present\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 1.1 Key Milestones in the Advancement of Natural Language Processing\u003cbr\u003e 1.2 Early history and turning points of machine translation  \u003cbr\u003e__1.2.1 The study of Artsruny and Troyansky\u003cbr\u003e __1.2.2 Weaver's Proposal and the Georgetown-IBM Experiment\u003cbr\u003e __1.2.3 Limitations of Early Machine Translation and a New Transformation\u003cbr\u003e 1.3 The Beginning of Artificial Intelligence\u003cbr\u003e __1.3.1 Turing's Question: Can Machines Think?\u003cbr\u003e __1.3.2 Limitations of the Turing Test\u003cbr\u003e 1.4 How does artificial intelligence learn?\u003cbr\u003e __1.4.1 Development of artificial intelligence learning mechanisms\u003cbr\u003e __1.4.2 Perceptron: The First Step in Artificial Intelligence Learning\u003cbr\u003e 1.5 Backpropagation Algorithm: A Revolution in Learning\u003cbr\u003e __1.5.1 Nonlinearity: The Key to Building Smarter AI\u003cbr\u003e __1.5.2 Backpropagation Algorithm\u003cbr\u003e 1.6 The Rise of Transformers: A New Era in NLP\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 2: GPT\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 2.1 Introduction and usage of Runpot\u003cbr\u003e __2.1.1 Runpot Membership Registration\u003cbr\u003e __2.1.2 Purchase Credits\u003cbr\u003e __2.1.3 Pod Configuration\u003cbr\u003e __2.1.4 Jupiter Lab\u003cbr\u003e 2.2 Data Preparation and Model Configuration\u003cbr\u003e 2.3 Building a Language Model\u003cbr\u003e __2.3.1 Library Description\u003cbr\u003e __2.3.2 __init__ function\u003cbr\u003e __2.3.3 forward method\u003cbr\u003e __2.3.4 generate method\u003cbr\u003e 2.4 Adding an Optimizer  \u003cbr\u003e__2.4.1 Passing data to the GPU\u003cbr\u003e __2.4.2 Creating a Loss Function\u003cbr\u003e __2.4.3 Review the entire code\u003cbr\u003e 2.5 Adding Self-Attention\u003cbr\u003e __2.5.1 How information is exchanged between characters (average method)\u003cbr\u003e __2.5.2 Exchange information faster with matrix multiplication operations\u003cbr\u003e __2.5.3 What is self-attention?\u003cbr\u003e __2.5.4 Why should we divide by dk?\u003cbr\u003e __2.5.5 Applying Self-Attention\u003cbr\u003e 2.6 Multihead Attention and Feedforward\u003cbr\u003e __2.6.1 Creating multi-head attention\u003cbr\u003e __2.6.2 Creating a feedforward\u003cbr\u003e 2.7 Creating Blocks\u003cbr\u003e 2.8 Creating a Tokenizer\u003cbr\u003e __2.8.1 Comparison of tokenization according to changes in vocab_size\u003cbr\u003e __2.8.2 Creating a tokenizer\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 3: Overall Fine Tuning\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 3.1 Preparing the entire fine-tuning data\u003cbr\u003e __3.1.1 Principles and types of overall fine tuning\u003cbr\u003e __3.1.2 Various tasks and datasets\u003cbr\u003e __3.1.3 Data Preprocessing\u003cbr\u003e 3.2 Analysis of Gemma and Llama 3 model structures\u003cbr\u003e __3.2.1 Gemma Model Structure Analysis\u003cbr\u003e __3.2.2 Comparison of Gemma and Gemma 2 Models\u003cbr\u003e __3.2.3 Llama 3 model structure analysis  \u003cbr\u003e__3.2.4 Comparison of GPT, Gemma, and Llama\u003cbr\u003e 3.3 GPU Parallelization Techniques\u003cbr\u003e __3.3.1 Data Parallelism\u003cbr\u003e __3.3.2 Model Parallelism\u003cbr\u003e __3.3.3 Pipeline Parallelization\u003cbr\u003e __3.3.4 Tensor Parallel Processing\u003cbr\u003e __3.3.5 FSDP\u003cbr\u003e 3.4 Fine-tuning Gemma-2B-it using a single GPU\u003cbr\u003e __3.4.1 Runpot Environment Settings\u003cbr\u003e __3.4.2 Preparing the Gemma model\u003cbr\u003e __3.4.3 Preparing the dataset\u003cbr\u003e __3.4.4 Checking the Gemma model's functions\u003cbr\u003e __3.4.5 Generating keyword data\u003cbr\u003e __3.4.6 Data Preprocessing\u003cbr\u003e __3.4.7 Separating datasets and setting up collators\u003cbr\u003e __3.4.8 Setting learning parameters\u003cbr\u003e __3.4.9 Defining Evaluation Metrics\u003cbr\u003e __3.4.10 Model Training and Evaluation\u003cbr\u003e __3.4.11 Testing the fine-tuned model\u003cbr\u003e 3.5 Fine-tuning Llama3.1-8B-instruct using multiple GPUs\u003cbr\u003e __3.5.1 Runpot Environment Settings\u003cbr\u003e __3.5.2 Llama 3.1 Learning Parameter Settings\u003cbr\u003e __3.5.3 Preparing the dataset\u003cbr\u003e __3.5.4 Llama 3.1 Model Parameter Settings\u003cbr\u003e __3.5.5 Examining the Llama 3.1 Model Training Code\u003cbr\u003e __3.5.6 Running Llama 3.1 model training\u003cbr\u003e __3.5.7 Wandb setup and usage\u003cbr\u003e __3.5.8 Testing the trained Llama 3.1 model  \u003cbr\u003e__3.5.9 Evaluating Generated Text Data with OpenAI\u003cbr\u003e __3.5.10 Calculating Grading Score\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 4: Efficient Parameter Tuning Techniques (PEFT)\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 4.1 LoRA Theory and Practice\u003cbr\u003e __4.1.1 LoRA Concept\u003cbr\u003e __4.1.2 Runpot Environment Settings\u003cbr\u003e __4.1.3 Preparing the Gemma-2-9B-it model\u003cbr\u003e __4.1.4 Data Preprocessing\u003cbr\u003e __4.1.5 LoRA parameter settings\u003cbr\u003e __4.1.6 Model Training\u003cbr\u003e __4.1.7 Testing the trained model\u003cbr\u003e __4.1.8 Evaluating model performance with OpenAI\u003cbr\u003e 4.2 QLoRA Theory and Practice\u003cbr\u003e __4.2.1 Understanding Quantization\u003cbr\u003e __4.2.2 Runpot Environment Settings\u003cbr\u003e __4.2.3 Preparing the dataset\u003cbr\u003e __4.2.4 Setting quantization parameters\u003cbr\u003e __4.2.5 Model Preparation\u003cbr\u003e __4.2.6 Parameter settings\u003cbr\u003e __4.2.7 Model Training\u003cbr\u003e __4.2.8 Uploading a model to the Hugging Face Hub\u003cbr\u003e __4.2.9 Testing the trained model\u003cbr\u003e __4.2.10 Evaluation using Exact Match\u003cbr\u003e __4.2.11 Evaluating with the OpenAI API\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Chapter 5: Serving with vLLM\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e 5.1 Paged Attention Principle\u003cbr\u003e 5.2 How to use vLLM\u003cbr\u003e 5.3 Accelerate LLaMA3 generation speed\u003cbr\u003e 5.4 Multi-LoRA using vLLM\u003cbr\u003e __5.4.1 Multi-LoRA Practice  \u003cbr\u003e__5.4.2 Practice in a laptop environment\u003cbr\u003e 5.5 Things to keep in mind when using Multi-LoRA\u003cbr\u003e\u003cbr\u003e \u003cb\u003e▣ Appendix\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e Mathematical Review of Backpropagation\u003cbr\u003e Backpropagation code review\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eDetailed image\u003c\/b\u003e \u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cdiv\u003e\u003cimg src=\"https:\/\/image.yes24.com\/momo\/TopCate5033\/MidCate3\/503224848.jpg\" border=\"0\" alt=\"Detailed Image 1\"\u003e\u003c\/div\u003e\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 December 17, 2024\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 348 pages | 175*235*15mm\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 9791158395629 \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":43893217787946,"sku":"138210","price":38.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0683\/2750\/5962\/files\/ae1b93daff6aaba591958e5d2fc2b2a1.jpg?v=1765392210","url":"https:\/\/librairie.coreenne.fr\/en\/products\/138210","provider":"LIBRAIRIE COREENNE","version":"1.0","type":"link"}