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

33,343 Aufrufe • vor 2 Jahren

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

Tom Yeh

105,044 Aufrufe • vor 2 Jahren

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

Tom Yeh

66,816 Aufrufe • vor 2 Jahren

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

106,897 Aufrufe • vor 2 Jahren

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

Tom Yeh

54,516 Aufrufe • vor 2 Jahren

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

35,911 Aufrufe • vor 6 Monaten

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

Tom Yeh

101,691 Aufrufe • vor 1 Jahr

the more i think about aiah being the muse... show more

‎‎aj

22,837 Aufrufe • vor 1 Monat

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

Miko

96,045 Aufrufe • vor 8 Monaten

QXR Head Multi Bug The head multi is higher... show more

Leakers On Duty

59,411 Aufrufe • vor 6 Monaten

Transformer by hand ✍️ ~ 6 steps walkthrough below... Open the hood of a transformer and the parts list is overwhelming: embeddings, positional encoding, attention weighting, self-attention, cross-attention, multi-head attention, layer norm, skip connections, softmax, linear, Nx, shifted right, query, key, value, masking. Which of those actually make the car run? Two of them. Attention weighting and the feed-forward network. Everything else is an enhancement to make it run faster and longer, which is how we got from a car to a truck, and to the word "large" in large language model. So I drew and calculated those two parts entirely by hand. Goal: push five features through one transformer block, filling in every cell yourself. 1. Given Five positions of input features, arriving from the previous block. 2. Attention matrix Let us feed all five features to a query-key module (QK) and read back an attention weight matrix, A. The details of that module are a post of their own. 3. Attention weighting We multiply the input features by A to get the attention weighted features, Z. Still five positions. The effect is to combine features *across positions*, horizontally: X1 becomes X1 + X2, X2 becomes X2 + X3, and so on. 4. First layer Let us feed all five weighted features into the first layer of the FFN. Multiply by the weights and biases. This time the combining happens *across feature dimensions*, vertically, and each feature grows from 3 numbers to 4. Note that every position goes through the same weight matrix. That is what "position-wise" means. 5. ReLU We cross out the negatives. They become zeros. 6. Second layer Let us bring it back down: 4 dimensions to 3. The output feeds the next block, which has a completely separate set of parameters, and the whole thing runs again. You have just calculated a transformer block by hand. ✍️ The takeaway: the two parts are doing two different jobs, and neither one alone is enough. Attention mixes *across positions*, so a feature can see its neighbours. The FFN mixes *across feature dimensions*, so each position can think about itself. Horizontal, then vertical. Then that pattern repeats N times, each block with its own separate set of weights. That is the Nx from the list up top, and that is what makes the transformer run. 💾 Save this post! #AIbyHand #Transformers #DeepLearningshow more

Tom Yeh

26,279 Aufrufe • vor 3 Monaten

AI is now improving its own model architectures and... show more

General Trajectory

62,930 Aufrufe • vor 1 Monat

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

62,508 Aufrufe • vor 6 Monaten