الاهتمام الذاتي من الصفر

Traditional database:
  Query: "capital of France"  -->  exact match  -->  "Paris"

Attention:
  Query: "capital of France"  -->  similarity to ALL keys  -->  weighted blend of ALL values

Input embeddings (sequence of n tokens, each d-dimensional):

  X = [x1, x2, x3, ..., xn]       shape: (n, d)

Three weight matrices:

  Wq  shape: (d, dk)
  Wk  shape: (d, dk)
  Wv  shape: (d, dv)

Projections:

  Q = X @ Wq    shape: (n, dk)      each token's query
  K = X @ Wk    shape: (n, dk)      each token's key
  V = X @ Wv    shape: (n, dv)      each token's value

             Wq
  x_i ------[*]------> q_i    "What am I looking for?"
       |
       |     Wk
       +----[*]------> k_i    "What do I contain?"
       |
       |     Wv
       +----[*]------> v_i    "What do I offer?"

Scores = Q @ K^T    shape: (n, n)

              k1    k2    k3    k4    k5
        +-----+-----+-----+-----+-----+
   q1   | 2.1 | 0.3 | 0.1 | 0.8 | 0.2 |   <- how much q1 attends to each key
        +-----+-----+-----+-----+-----+
   q2   | 0.4 | 1.9 | 0.7 | 0.1 | 0.3 |
        +-----+-----+-----+-----+-----+
   q3   | 0.2 | 0.6 | 2.3 | 0.5 | 0.1 |
        +-----+-----+-----+-----+-----+
   q4   | 0.9 | 0.1 | 0.4 | 1.7 | 0.6 |
        +-----+-----+-----+-----+-----+
   q5   | 0.1 | 0.3 | 0.2 | 0.5 | 2.0 |
        +-----+-----+-----+-----+-----+

Each row: one token's attention over the entire sequence

Raw scores for q1:   [2.1, 0.3, 0.1, 0.8, 0.2]
                            |
                         softmax
                            |
Attention weights:   [0.52, 0.09, 0.07, 0.14, 0.08]   (sums to ~1.0)

output_i = sum( attention_weight[i][j] * v_j  for all j )

For token 1:
  output_1 = 0.52 * v1 + 0.09 * v2 + 0.07 * v3 + 0.14 * v4 + 0.08 * v5

import numpy as np

def softmax(x):
    shifted = x - np.max(x, axis=-1, keepdims=True)
    exp_x = np.exp(shifted)
    return exp_x / np.sum(exp_x, axis=-1, keepdims=True)

logits = np.array([2.0, 1.0, 0.1])
print(f"logits:  {logits}")
print(f"softmax: {softmax(logits)}")
print(f"sum:     {softmax(logits).sum():.4f}")

def scaled_dot_product_attention(Q, K, V):
    dk = Q.shape[-1]
    scores = Q @ K.T / np.sqrt(dk)
    weights = softmax(scores)
    output = weights @ V
    return output, weights

class SelfAttention:
    def __init__(self, d_model, dk, dv, seed=42):
        rng = np.random.default_rng(seed)
        scale = np.sqrt(2.0 / (d_model + dk))
        self.Wq = rng.normal(0, scale, (d_model, dk))
        self.Wk = rng.normal(0, scale, (d_model, dk))
        scale_v = np.sqrt(2.0 / (d_model + dv))
        self.Wv = rng.normal(0, scale_v, (d_model, dv))
        self.dk = dk

    def forward(self, X):
        Q = X @ self.Wq
        K = X @ self.Wk
        V = X @ self.Wv
        output, weights = scaled_dot_product_attention(Q, K, V)
        return output, weights

sentence = ["The", "cat", "sat", "on", "the", "mat"]
n_tokens = len(sentence)
d_model = 8
dk = 4
dv = 4

rng = np.random.default_rng(42)
X = rng.normal(0, 1, (n_tokens, d_model))

attn = SelfAttention(d_model, dk, dv, seed=42)
output, weights = attn.forward(X)

print("Attention weights (each row: where that token looks):\n")
print(f"{'':>6}", end="")
for token in sentence:
    print(f"{token:>6}", end="")
print()

for i, token in enumerate(sentence):
    print(f"{token:>6}", end="")
    for j in range(n_tokens):
        w = weights[i][j]
        print(f"{w:6.3f}", end="")
    print()

def ascii_heatmap(weights, tokens, chars=" ░▒▓█"):
    n = len(tokens)
    print(f"\n{'':>6}", end="")
    for t in tokens:
        print(f"{t:>6}", end="")
    print()

    for i in range(n):
        print(f"{tokens[i]:>6}", end="")
        for j in range(n):
            level = int(weights[i][j] * (len(chars) - 1) / weights.max())
            level = min(level, len(chars) - 1)
            print(f"{'  ' + chars[level] + '   '}", end="")
        print()

ascii_heatmap(weights, sentence)

import torch
import torch.nn as nn

d_model = 8
n_heads = 2
seq_len = 6

mha = nn.MultiheadAttention(embed_dim=d_model, num_heads=n_heads, batch_first=True)

X_torch = torch.randn(1, seq_len, d_model)

output, attn_weights = mha(X_torch, X_torch, X_torch)

print(f"Input shape:            {X_torch.shape}")
print(f"Output shape:           {output.shape}")
print(f"Attention weight shape: {attn_weights.shape}")
print(f"\nAttn weights (averaged over heads):")
print(attn_weights[0].detach().numpy().round(3))