Large Language Models explains how modern AI systems are designed, trained, evaluated, deployed, and used. Beginning with the foundations of generative AI and Transformer architecture, the book explores tokenization, embeddings, pretraining, fine-tuning, instruction tuning, prompting, multimodal AI, retrieval-augmented generation, vector search, tool calling, AI agents, evaluation, safety, deployment, and continuous improvement. It also examines major AI ecosystems and shows how to compare models by capability, reliability, latency, cost, safety, and practical fit rather than by hype alone. The final chapters provide a practical framework for designing an LLM from a problem statement through data, tokenizer, architecture, training, post-training, evaluation, deployment, monitoring, and controlled improvement.
Prijshistorie
* Prijshistorie bevat geen data van Amazon, Amazon Marketplace.
Prijzen voor het laatst bijgewerkt op: