Question 12: Which of the following statements about the Transformer …

Select all that apply.

1. A

   Masking (look-ahead mask) is applied in every decoder self-attention layer, not just the first one.

2. B

   Token embeddings are used in the encoder but not in the decoder.

3. C

   Positional encoding is required only in the encoder, not in the decoder.

4. D

   Token embeddings are used in both the encoder and the decoder.

5. E

   Positional encodings are added to the input embeddings in both the encoder and the decoder.