Post-Training: A Practical Guide for AI Engineers and Developers - Chris Von Csefalvay - Marjane Mall - Image 1
220
00DH
300.00 DH
-27%

Post-Training: A Practical Guide for AI Engineers and Developers - Chris Von Csefalvay

Livraison

Détails
Frais de livraison à partir de :
Livraison entre le Jeudi 10 septembre 2026 et le Vendredi 11 septembre 2026

À propos de cet article :

Marque : GENERIC
Vendu par HEAVENBOOKS.MA

Découvrez comment transformer des modèles d'IA fondamentaux en systèmes prêts pour la production grâce à cet ouvrage pratique de Chris Von Csefalvay. Ce guide complet explore les techniques essentielles pour affiner les modèles, les aligner sur vos valeurs et les déployer avec fiabilité, en abordant des concepts clés comme le fine-tuning (LoRA, QLo...

1

Mode de paiement

Paiement par carte bancaire
Carte marocaines
Paiement à la livraison
Paiement en espèce à la livraison
Politique de retours
Note de politique de retour

Description produit

Marque
GENERIC
Titre
Post-Training: A Practical Guide for AI Engineers and Developers
Éditeur
No Starch Press
Type de produit
Paperback
Présentation du livre
Paperback
Date de sortie
9/1/2026 12:00:00 AM
Langue d'origine
English
ISBN
1718505213
Langue
English
Résumé
Capable by default. Reliable by design.If you're a practitioner who has watched a promising AI demo fail to survive contact with production, where prompting hits its ceiling, retrieval isn't enough, and the model still can't be trusted with your domain, post-training is what you've been missing.Post-Training is a practical guide to turning foundation models into production-ready systems — reshaping behavior, aligning to your values, and deploying with confidence. Each technique is taught concept-first, then implementation-through-code, so you understand not just what to run, but what you're actually changing inside the model.You'll leave with the skills to:Fine-tune models on curated datasets using supervised fine-tuning, LoRA, and QLoRA without destroying the base model's general capabilitiesApply reinforcement learning from human feedback and modern preference optimization methods, including GRPO, ORPO, and beyond, to shape model behaviorEvaluate models rigorously: design benchmarks, detect regression, and measure quality claims that survive scrutinyAdapt models to specialized domains, from clinical language to legal text, turning general capability into a defensible competitive advantageTrain agentic models that take sequences of actions reliably, not just models that talk about taking actionsQuantize and compress fine-tuned models for deployment without sacrificing the gains you trained forPost-training is where models stop being impressive and start being useful. This book teaches you to do it right. Read more
Auteur
Chris Von Csefalvay
Date de parution
9/1/2026 12:00:00 AM