(`torch.FloatTensor`): input to the layer of shape `(seq_len, batch, embed_dim)`
            attention_mask (`torch.FloatTensor`): attention mask of size
                `(batch, 1, target_len, source_len)` where padding elements are indicated by very large negative
                values.
            position_embeddings (`torch.FloatTensor`, *optional*): position embeddings, to be added to hidden_states.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
        )