ronen
February 27, 2022, 6:00pm
1
Hi,
In contrast, I’d like to use the Transformers PyTorch T5 implementation if possible. The option seems to be available for BERT:
self.num_attention_heads = config.num_attention_heads
self.attention_head_size = int(config.hidden_size / config.num_attention_heads)
self.all_head_size = self.num_attention_heads * self.attention_head_size
self.query = nn.Linear(config.hidden_size, self.all_head_size)
self.key = nn.Linear(config.hidden_size, self.all_head_size)
self.value = nn.Linear(config.hidden_size, self.all_head_size)
self.dropout = nn.Dropout(config.attention_probs_dropout_prob)
self.position_embedding_type = position_embedding_type or getattr(
config, "position_embedding_type", "absolute"
)
if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query":
self.max_position_embeddings = config.max_position_embeddings
self.distance_embedding = nn.Embedding(2 * config.max_position_embeddings - 1, self.attention_head_size)
self.is_decoder = config.is_decoder
def transpose_for_scores(self, x: torch.Tensor) -> torch.Tensor:
new_x_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size)
But for T5 I haven’t been able to find an equivalent- the encoder_attention_mask there is of dimension (batch_size, encoder_seq_len):
# required mask seq length can be calculated via length of past
mask_seq_length = past_key_values[0][0].shape[2] + seq_length if past_key_values is not None else seq_length
if use_cache is True:
assert self.is_decoder, f"`use_cache` can only be set to `True` if {self} is used as a decoder"
if attention_mask is None:
attention_mask = torch.ones(batch_size, mask_seq_length).to(inputs_embeds.device)
if self.is_decoder and encoder_attention_mask is None and encoder_hidden_states is not None:
encoder_seq_length = encoder_hidden_states.shape[1]
encoder_attention_mask = torch.ones(
batch_size, encoder_seq_length, device=inputs_embeds.device, dtype=torch.long
)
# initialize past_key_values with `None` if past does not exist
if past_key_values is None:
past_key_values = [None] * len(self.block)
# We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length]
# ourselves in which case we just need to make it broadcastable to all heads.
extended_attention_mask = self.get_extended_attention_mask(attention_mask, input_shape, inputs_embeds.device)
Anyone have experience with this?
