Hello, in here
|
# Convert to Bart output format: (seq_len, BS, model_dim) -> (BS, seq_len, model_dim) |
I think the comment should be
# Convert to Bart output format: (BS, seq_len, model_dim) -> (seq_len, BS, model_dim)
Before transpose , shape of x and encoder_hidden_states are both (BS, seq_len, model_dim) to me.
Thanks.
Hello, in here
transformers/src/transformers/modeling_bart.py
Line 588 in 0770879
I think the comment should be
Before transpose , shape of x and encoder_hidden_states are both (BS, seq_len, model_dim) to me.
Thanks.