chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,288 @@
|
||||
'''
|
||||
The codes are modified based on huggingface transformers library.
|
||||
'''
|
||||
|
||||
import math
|
||||
from typing import Optional, Tuple
|
||||
|
||||
import torch
|
||||
import torch.utils.checkpoint
|
||||
from torch import nn
|
||||
from transformers.modeling_utils import (
|
||||
apply_chunking_to_forward,
|
||||
find_pruneable_heads_and_indices,
|
||||
prune_linear_layer,
|
||||
)
|
||||
from transformers.models.bert.modeling_bert import BertIntermediate, BertOutput, BertSelfOutput
|
||||
from transformers.utils import (
|
||||
logging,
|
||||
)
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class BertSelfAttention(nn.Module):
|
||||
def __init__(self, config, position_embedding_type=None):
|
||||
super().__init__()
|
||||
if config.hidden_size % config.num_attention_heads != 0 and not hasattr(config, "embedding_size"):
|
||||
raise ValueError(
|
||||
f"The hidden size ({config.hidden_size}) is not a multiple of the number of attention "
|
||||
f"heads ({config.num_attention_heads})"
|
||||
)
|
||||
|
||||
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):
|
||||
new_x_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size)
|
||||
x = x.view(new_x_shape)
|
||||
return x.permute(0, 2, 1, 3)
|
||||
|
||||
def forward(
|
||||
self,
|
||||
query,
|
||||
key,
|
||||
value,
|
||||
attention_mask: Optional[torch.FloatTensor] = None,
|
||||
head_mask: Optional[torch.FloatTensor] = None,
|
||||
encoder_hidden_states: Optional[torch.FloatTensor] = None,
|
||||
encoder_attention_mask: Optional[torch.FloatTensor] = None,
|
||||
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
|
||||
output_attentions: Optional[bool] = False,
|
||||
) -> Tuple[torch.Tensor]:
|
||||
mixed_query_layer = self.query(query)
|
||||
|
||||
# If this is instantiated as a cross-attention module, the keys
|
||||
# and values come from an encoder; the attention mask needs to be
|
||||
# such that the encoder's padding tokens are not attended to.
|
||||
is_cross_attention = encoder_hidden_states is not None
|
||||
|
||||
if is_cross_attention and past_key_value is not None:
|
||||
# reuse k,v, cross_attentions
|
||||
key_layer = past_key_value[0]
|
||||
value_layer = past_key_value[1]
|
||||
attention_mask = encoder_attention_mask
|
||||
elif is_cross_attention:
|
||||
key_layer = self.transpose_for_scores(self.key(encoder_hidden_states))
|
||||
value_layer = self.transpose_for_scores(self.value(encoder_hidden_states))
|
||||
attention_mask = encoder_attention_mask
|
||||
elif past_key_value is not None:
|
||||
key_layer = self.transpose_for_scores(self.key(key))
|
||||
value_layer = self.transpose_for_scores(self.value(value))
|
||||
key_layer = torch.cat([past_key_value[0], key_layer], dim=2)
|
||||
value_layer = torch.cat([past_key_value[1], value_layer], dim=2)
|
||||
else:
|
||||
key_layer = self.transpose_for_scores(self.key(key))
|
||||
value_layer = self.transpose_for_scores(self.value(value))
|
||||
|
||||
query_layer = self.transpose_for_scores(mixed_query_layer)
|
||||
|
||||
if self.is_decoder:
|
||||
# if cross_attention save Tuple(torch.Tensor, torch.Tensor) of all cross attention key/value_states.
|
||||
# Further calls to cross_attention layer can then reuse all cross-attention
|
||||
# key/value_states (first "if" case)
|
||||
# if uni-directional self-attention (decoder) save Tuple(torch.Tensor, torch.Tensor) of
|
||||
# all previous decoder key/value_states. Further calls to uni-directional self-attention
|
||||
# can concat previous decoder key/value_states to current projected key/value_states (third "elif" case)
|
||||
# if encoder bi-directional self-attention `past_key_value` is always `None`
|
||||
past_key_value = (key_layer, value_layer)
|
||||
|
||||
# Take the dot product between "query" and "key" to get the raw attention scores.
|
||||
attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
|
||||
|
||||
if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query":
|
||||
seq_length = query.size()[1]
|
||||
position_ids_l = torch.arange(seq_length, dtype=torch.long, device=query.device).view(-1, 1)
|
||||
position_ids_r = torch.arange(seq_length, dtype=torch.long, device=query.device).view(1, -1)
|
||||
distance = position_ids_l - position_ids_r
|
||||
positional_embedding = self.distance_embedding(distance + self.max_position_embeddings - 1)
|
||||
positional_embedding = positional_embedding.to(dtype=query_layer.dtype) # fp16 compatibility
|
||||
|
||||
if self.position_embedding_type == "relative_key":
|
||||
relative_position_scores = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding)
|
||||
attention_scores = attention_scores + relative_position_scores
|
||||
elif self.position_embedding_type == "relative_key_query":
|
||||
relative_position_scores_query = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding)
|
||||
relative_position_scores_key = torch.einsum("bhrd,lrd->bhlr", key_layer, positional_embedding)
|
||||
attention_scores = attention_scores + relative_position_scores_query + relative_position_scores_key
|
||||
|
||||
attention_scores = attention_scores / math.sqrt(self.attention_head_size)
|
||||
if attention_mask is not None:
|
||||
# Apply the attention mask is (precomputed for all layers in BertModel forward() function)
|
||||
attention_scores = attention_scores + attention_mask
|
||||
|
||||
# Normalize the attention scores to probabilities.
|
||||
attention_probs = nn.functional.softmax(attention_scores, dim=-1)
|
||||
|
||||
# This is actually dropping out entire tokens to attend to, which might
|
||||
# seem a bit unusual, but is taken from the original Transformer paper.
|
||||
attention_probs = self.dropout(attention_probs)
|
||||
|
||||
# Mask heads if we want to
|
||||
if head_mask is not None:
|
||||
attention_probs = attention_probs * head_mask
|
||||
|
||||
context_layer = torch.matmul(attention_probs, value_layer)
|
||||
|
||||
context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
|
||||
new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
|
||||
context_layer = context_layer.view(new_context_layer_shape)
|
||||
|
||||
outputs = (context_layer, attention_probs) if output_attentions else (context_layer,)
|
||||
|
||||
if self.is_decoder:
|
||||
outputs = outputs + (past_key_value,)
|
||||
return outputs
|
||||
|
||||
|
||||
class BertAttention(nn.Module):
|
||||
def __init__(self, config, position_embedding_type=None):
|
||||
super().__init__()
|
||||
self.self = BertSelfAttention(config, position_embedding_type=position_embedding_type)
|
||||
self.output = BertSelfOutput(config)
|
||||
self.pruned_heads = set()
|
||||
|
||||
def prune_heads(self, heads):
|
||||
if len(heads) == 0:
|
||||
return
|
||||
heads, index = find_pruneable_heads_and_indices(
|
||||
heads, self.self.num_attention_heads, self.self.attention_head_size, self.pruned_heads
|
||||
)
|
||||
|
||||
# Prune linear layers
|
||||
self.self.query = prune_linear_layer(self.self.query, index)
|
||||
self.self.key = prune_linear_layer(self.self.key, index)
|
||||
self.self.value = prune_linear_layer(self.self.value, index)
|
||||
self.output.dense = prune_linear_layer(self.output.dense, index, dim=1)
|
||||
|
||||
# Update hyper params and store pruned heads
|
||||
self.self.num_attention_heads = self.self.num_attention_heads - len(heads)
|
||||
self.self.all_head_size = self.self.attention_head_size * self.self.num_attention_heads
|
||||
self.pruned_heads = self.pruned_heads.union(heads)
|
||||
|
||||
def forward(
|
||||
self,
|
||||
query: torch.Tensor,
|
||||
key: torch.Tensor,
|
||||
value: torch.Tensor,
|
||||
attention_mask: Optional[torch.FloatTensor] = None,
|
||||
head_mask: Optional[torch.FloatTensor] = None,
|
||||
encoder_hidden_states: Optional[torch.FloatTensor] = None,
|
||||
encoder_attention_mask: Optional[torch.FloatTensor] = None,
|
||||
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
|
||||
output_attentions: Optional[bool] = False,
|
||||
) -> Tuple[torch.Tensor]:
|
||||
self_outputs = self.self(
|
||||
query, key, value,
|
||||
attention_mask,
|
||||
head_mask,
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
past_key_value,
|
||||
output_attentions,
|
||||
)
|
||||
attention_output = self.output(self_outputs[0], query)
|
||||
outputs = (attention_output,) + self_outputs[1:] # add attentions if we output them
|
||||
return outputs
|
||||
|
||||
|
||||
class BertLayerForDecoder(nn.Module):
|
||||
def __init__(self, config):
|
||||
super().__init__()
|
||||
self.chunk_size_feed_forward = config.chunk_size_feed_forward
|
||||
self.seq_len_dim = 1
|
||||
self.attention = BertAttention(config)
|
||||
self.is_decoder = config.is_decoder
|
||||
self.add_cross_attention = config.add_cross_attention
|
||||
if self.add_cross_attention:
|
||||
if not self.is_decoder:
|
||||
raise ValueError(f"{self} should be used as a decoder model if cross attention is added")
|
||||
self.crossattention = BertAttention(config, position_embedding_type="absolute")
|
||||
self.intermediate = BertIntermediate(config)
|
||||
self.output = BertOutput(config)
|
||||
|
||||
def forward(
|
||||
self,
|
||||
query: torch.Tensor,
|
||||
key: torch.Tensor,
|
||||
value: torch.Tensor,
|
||||
attention_mask: Optional[torch.FloatTensor] = None,
|
||||
head_mask: Optional[torch.FloatTensor] = None,
|
||||
encoder_hidden_states: Optional[torch.FloatTensor] = None,
|
||||
encoder_attention_mask: Optional[torch.FloatTensor] = None,
|
||||
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None,
|
||||
output_attentions: Optional[bool] = False,
|
||||
) -> Tuple[torch.Tensor]:
|
||||
# decoder uni-directional self-attention cached key/values tuple is at positions 1,2
|
||||
self_attn_past_key_value = past_key_value[:2] if past_key_value is not None else None
|
||||
self_attention_outputs = self.attention(
|
||||
query, key, value,
|
||||
attention_mask,
|
||||
head_mask,
|
||||
output_attentions=output_attentions,
|
||||
past_key_value=self_attn_past_key_value,
|
||||
)
|
||||
attention_output = self_attention_outputs[0]
|
||||
|
||||
# if decoder, the last output is tuple of self-attn cache
|
||||
if self.is_decoder:
|
||||
outputs = self_attention_outputs[1:-1]
|
||||
present_key_value = self_attention_outputs[-1]
|
||||
else:
|
||||
outputs = self_attention_outputs[1:] # add self attentions if we output attention weights
|
||||
|
||||
cross_attn_present_key_value = None
|
||||
if self.is_decoder and encoder_hidden_states is not None:
|
||||
if not hasattr(self, "crossattention"):
|
||||
raise ValueError(
|
||||
f"If `encoder_hidden_states` are passed, {self} has to be instantiated with cross-attention layers by setting `config.add_cross_attention=True`"
|
||||
)
|
||||
|
||||
# cross_attn cached key/values tuple is at positions 3,4 of past_key_value tuple
|
||||
cross_attn_past_key_value = past_key_value[-2:] if past_key_value is not None else None
|
||||
cross_attention_outputs = self.crossattention(
|
||||
attention_output,
|
||||
attention_mask,
|
||||
head_mask,
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
cross_attn_past_key_value,
|
||||
output_attentions,
|
||||
)
|
||||
attention_output = cross_attention_outputs[0]
|
||||
outputs = outputs + cross_attention_outputs[1:-1] # add cross attentions if we output attention weights
|
||||
|
||||
# add cross-attn cache to positions 3,4 of present_key_value tuple
|
||||
cross_attn_present_key_value = cross_attention_outputs[-1]
|
||||
present_key_value = present_key_value + cross_attn_present_key_value
|
||||
|
||||
layer_output = apply_chunking_to_forward(
|
||||
self.feed_forward_chunk, self.chunk_size_feed_forward, self.seq_len_dim, attention_output
|
||||
)
|
||||
outputs = (layer_output,) + outputs
|
||||
|
||||
# if decoder, return the attn key/values as the last output
|
||||
if self.is_decoder:
|
||||
outputs = outputs + (present_key_value,)
|
||||
|
||||
return outputs
|
||||
|
||||
def feed_forward_chunk(self, attention_output):
|
||||
intermediate_output = self.intermediate(attention_output)
|
||||
layer_output = self.output(intermediate_output, attention_output)
|
||||
return layer_output
|
||||
Reference in New Issue
Block a user