Grundkonzepte
LLM
Large Language Model — a neural network trained on vast text corpora to generate human-like text.
A Large Language Model is a transformer-based neural network with billions of parameters trained on internet-scale text data. LLMs learn to predict the next token, which emergently produces reasoning, coding, translation, and creative capabilities. GPT-4, Claude, and Gemini are all LLMs.
Verwandte Begriffe
Transformer
The neural network architecture underlying virtually all modern LLMs.
Foundation Model
A large pre-trained model that serves as the base for many downstream applications.
Parameter
A learnable weight in a neural network; model size is measured in billions of parameters.
Pre-Training
The initial large-scale training phase where a model learns language from massive text corpora.