The comment in the Bi-LSTM (Attention) model has an issue.

The comment `# output : [batch_size, len_seq, n_hidden]` should indeed be corrected to `# output : [batch_size, len_seq, n_hidden*2]` because the Bi-LSTM model is bidirectional. In a bidirectional LSTM, the hidden size is effectively doubled, as it concatenates the forward and backward hidden states. Therefore, the correct shape of the `output` after permutation is `[batch_size, len_seq, n_hidden * 2]`.

Locate the Bi-LSTM (Attention) model notebook and read the surrounding output permutation code and comment. Correct the documented output shape to include the bidirectional hidden size, then verify that the comment matches the model's actual output dimensions.

Written by the indexing model from the issue text.