# Real sentences have many words
seq_len = 10  # 10 words in sentence
d_model = 64  # Each word is 64-dimensional vector

# Q, K, V matrices transform word vectors
Q = torch.randn(seq_len, d_model)  # Queries for each word
K = torch.randn(seq_len, d_model)  # Keys for each word
V = torch.randn(seq_len, d_model)  # Values for each word