Concepts Fondamentaux
Foundation Model
A large pre-trained model that serves as the base for many downstream applications.
Foundation models are trained at massive scale on diverse data and designed to be adapted for many tasks via fine-tuning or prompting. The term emphasizes that these models form the foundation on which specialized AI systems are built. All major commercial LLMs — GPT-5, Claude, Gemini — are foundation models.
Termes Associés
LLM (Grand Modèle de Langage)
Un réseau de neurones entraîné sur de grands volumes de texte pour générer du contenu.
Pre-Training
The initial large-scale training phase where a model learns language from massive text corpora.
İnce Ayar (Fine-Tuning)
Önceden eğitilmiş bir modeli belirli bir görev veya veri kümesi için özelleştirme işlemi.
Instruction Tuning
Fine-tuning a model on examples of instructions paired with ideal responses.