Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

multi-head attention

Running several attention computations in parallel on different learned projections, then combining the results.

Examples

Eight attention heads let a Transformer layer track eight different relationships between tokens at once, in parallel.