Name: Transformer: Multi-Head Attention ~ Math vs Code 🔢💻 ~ I made this visualization to show you how to implement the multi-head attention math in PyTorch within 50 LoC. Multi-Head Attention is what makes the Transformer's performance outstanding. It captures and represents more diverse linguistic relationships and patterns, and attends to different learned input embedding spaces. The parallel computing design also makes the model more efficient.
Uploaded: 2024-10-07T13:04:42.000Z
Duration: PT10.065S
Channel: Yan Chen

Transformer: Multi-Head Attention ~ Math vs Code 🔢💻 ~... show more

Yan Chen

33,255 Aufrufe • vor 1 Jahr

AlphaFold by hand✍️ Excel ~ I designed this exercise... show more

Tom Yeh

104,965 Aufrufe • vor 1 Jahr

THE BEST visual explainer of how information propagates through... a transformer. If you want to have more than intuition about how the Transformer architecture is ruling the LLM world - open-source project explains everything about LLM Transformer Models! - A great resource for anyone looking to gain a deeper understanding of how Transformer-based AI models like GPT work, including: - Self-attention mechanisms - Encoder-decoder architecture - Positional encoding - Multi-head attentionshow more

Rohan Paul

106,880 Aufrufe • vor 1 Jahr

Autoencoder by hand✍️Excel~ I designed this exercise to show... show more

Tom Yeh

54,473 Aufrufe • vor 1 Jahr

Single vs Multi-hand Attention by hand ✍️ Resize matrices... yourself 👉 The most important fact about multi-head attention: it has the same parameter count as single-head attention. The difference is purely structural — same total Wqkv weights, partitioned into smaller q–k–v triples. Look at the two diagrams below. Both Wqkv matrices have the same height — same number of weight rows, same number of parameters. What changes is how that single tall block is sliced. • Left. One head. The full Wqkv produces one big QKV: a tall Q (36 rows), a tall K, a tall V. One scoring computation runs over those full-width tensors. • Right. 3 heads. The same-height Wqkv is sliced into 3 smaller q–k–v triples — each 12 rows tall. 3 scoring computations run in parallel, each a thinner version of the left. The compute trade-off — kind of. Same Wqkv weights. Multi-head runs the attention scoring S = Kᵀ × Q once per head, so the dot-product count multiplies by H. • Single-head: seq × seq = 40² = 1600 dot products • Multi-head: seq × seq × H = 40² × 3 = 4800 dot products (3×) But each multi-head dot product is narrower — its inner dimension is head_dim instead of H × head_dim. So when you count actual scalar multiplications, the totals are equal: • Single-head: seq² × (H × head_dim) = 40² × 36 = 57600 • Multi-head: seq² × H × head_dim = 40² × 3 × 12 = 57600 Same FLOPs. Multi-head buys you H independent attention patterns at no extra weight cost and no extra arithmetic cost — it's the same total compute, sliced into H finer-grained heads.show more

Tom Yeh

35,046 Aufrufe • vor 1 Monat

Autoencoder by hand✍️Excel~ I designed this exercise to show... show more

Tom Yeh

101,555 Aufrufe • vor 1 Jahr

kling 3.0 is crazy... this model works very different... show more

Miko

95,568 Aufrufe • vor 4 Monaten

Self Attention vs Cross Attention by hand ✍️ Resize... the matrices yourself 👉 Two attention mechanisms, side by side. Both project X into queries; both compute attention via S = Kᵀ × Q and F = V × A. The only difference is the source of K and V. Self attention uses X for everything. Q, K, and V all come from projecting X. Each X token attends to every other X token. The score matrix S is square — 128 × 128. Cross attention uses X for queries and a second sequence E for keys and values. Each X token attends to every E token instead. The score matrix S is rectangular — 64 × 128. Notice what's shared and what's not: X is the same in both — same 36 × 128 input. Q and K share the 16 dimension — that's what makes the dot product Kᵀ × Q valid in either case. V dimensions are independent: self-attention uses 12, cross-attention uses 12. The choice doesn't depend on which mechanism you're using; it depends on what output dimension your downstream layer expects.show more

Tom Yeh

61,300 Aufrufe • vor 1 Monat