The neural network design behind most large language models, which uses self-attention to process every part of a sequence in parallel.
The Transformer Architecture is the design behind the current generation of AI models, including most LLMs. Using self-attention, Transformers process entire sequences of text in parallel (unlike sequential RNNs), which lets them capture long-range dependencies and context.
See also Self-Attention, Large Language Model, Fine-Tuning and Model Inference.