NLP & LLMs¶
Natural language processing (NLP) turns text — an unstructured, discrete, variable-length signal — into numeric structures a model can compute with, then back into text a human can read. This chapter traces the full path tokenization → embeddings → attention/Transformers → large language models (LLMs), derives the attention mechanism from first principles with a fully worked numeric example, and covers the practical toolkit that dominates modern NLP in production: pre-training, alignment, fine-tuning (full, LoRA, QLoRA), retrieval-augmented generation (RAG), prompting, decoding, quantization, and serving. …
🔒 La suite est en accès freemium — lecture complète 100 % gratuite
Tu lis ici l'aperçu libre. Le reste du chapitre (code, schémas, maths, exercices) fait partie du livre complet : crée un compte gratuit (30 secondes, aucun paiement) pour tout lire.