# Attention dimensions
d_model = 64
num_heads = 8
d_k = d_model // num_heads  # 8

# Linear transformations to create Q, K, V
W_q = nn.Linear(d_model, d_model, bias=False)
W_k = nn.Linear(d_model, d_model, bias=False)
W_v = nn.Linear(d_model, d_model, bias=False)

# Transform embeddings
Q = W_q(embeddings)  # Queries: "What am I looking for?"
K = W_k(embeddings)  # Keys: "What do I represent?"
V = W_v(embeddings)  # Values: "What information do I carry?"

print(f"Q shape: {Q.shape}")  # [6, 64]
print(f"K shape: {K.shape}")  # [6, 64]
print(f"V shape: {V.shape}")  # [6, 64]