Aan de slagGa gratis aan de slag

Implementing multi-head attention

Before you dive in and begin building your own MultiHeadAttention class, you'll try out using the class to see how it transforms the query, key, and value matrices. Recall that these matrices are generated by projecting the input embeddings using linear transformations with learned weights.

query, key, and value matrices have already been created for you, and the MultiHeadAttention has been defined for you.

Deze oefening maakt deel uit van de cursus

Transformer Models with PyTorch

Cursus bekijken

Oefeninstructies

  • Define the attention parameters for eight attention heads and input embeddings with a dimensionality of 512.
  • Create an instance of the MultiHeadAttention class using the defined parameters.
  • Pass the query, key, and value matrices through the multihead_attn mechanism.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Define attention parameters
d_model = ____
num_heads = ____

# Instantiate a MultiHeadAttention instance
multihead_attn = ____

# Pass the query, key, and value matrices through the mechanism
output = ____
print(output.shape)
Code bewerken en uitvoeren