Fine-Tuning Large Language Models

From Custom Datasets to High-Performance AI Models Using Modern Toolchains

29,95 €

inkl. MwSt. und Versand · Lieferzeit 1–2 Werktage

Gesetzliche Gewährleistung: 2 Jahre · Details

Nur noch 1 verfügbar

Beschreibung

Are your prompts not cutting it anymore? Fine-tuning is the next level. This hands-on guide takes you from zero to deploying your own<br>custom-trained large language model using real code, modern tools, <br>&gt;Whether you want to build a medical assistant, legal document analyzer, <br>coding AI, or customer support bot, this book gives you the exact<br>&gt;What you'll learn: - How fine-tuning differs from prompt engineering and RAG and when<br> to use each<br>- LoRA and QLoRA: fine-tune powerful models on a single GPU<br>- How to collect, clean, and format high-quality instruction datasets<br>- Supervised Fine-Tuning (SFT), RLHF, and Direct Preference Optimization<br>- Advanced techniques: mixed precision, gradient checkpointing, <br> multi-GPU training<br>- How to evaluate, quantize, and deploy your model to production<br>- Safety, bias mitigation, and responsible AI practices<br>- 14 chapters of step-by-step projects including a chatbot, <br>&gt;This is not a theory book. Every chapter includes working Python code<br>using Hugging Face Transformers, PEFT, TRL, and modern open-source<br>&gt;By the end, you won't just understand fine-tuning you'll have built<br>&gt;Perfect for: ML engineers, Python developers, data scientists, and<br>anyone ready to move beyond ChatGPT and take control of their AI stack.

Artikeldetails

EAN

9798182313315

Sprache

Englisch

Einband / Art

Taschenbuch

Maße

228 x 151 x 16 mm

Erscheinungsjahr

2026

Verlag / Hersteller

Independently published