Which architecture forms the foundation of modern Large Language Models like GPT and LLaMA?
- CNN
- RNN
- Transformer
- LSTM
Answer: Transformer
Transformer architecture (Vaswani et al., 2017) uses self-attention mechanisms to process sequences in parallel, enabling scaling to billions of parameters. Foundation for GPT, BERT, LLaMA, and other LLMs. Critical for understanding modern AI systems.