Tokens → embeddings + positional encoding → N encoder blocks.

Tokens → embeddings + positional encoding → N encoder blocks. Each block: (1) Multi-head self-attention: Q, K, V projections → attention = softmax(QKᵀ/√d_k)V. (2) Add & LayerNorm. (3) Feed-forward (two linear layers + ReLU). (4) Add & LayerNorm. Decoder adds cross-attention over encoder output. Final → linear + softmax over vocabulary.