File size: 14,748 Bytes
37b9eb5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 | import math
from typing import Optional, Tuple, Union
import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers import PreTrainedModel, PretrainedConfig
from transformers.modeling_outputs import BaseModelOutputWithPooling, MaskedLMOutput
from .configuration_bert_updated import BertUpdatedConfig
class BertSelfAttention(nn.Module):
def __init__(self, config):
super().__init__()
self.num_attention_heads = config.num_attention_heads
self.attention_head_size = 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)
def _split_heads(self, x: torch.Tensor) -> torch.Tensor:
B, T, _ = x.shape
return x.view(B, T, self.num_attention_heads, self.attention_head_size).permute(0, 2, 1, 3)
def forward(
self,
hidden_states: torch.Tensor,
key_padding_mask: Optional[torch.Tensor] = None,
output_attentions: bool = False,
) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
q = self._split_heads(self.query(hidden_states))
k = self._split_heads(self.key(hidden_states))
v = self._split_heads(self.value(hidden_states))
scale = math.sqrt(self.attention_head_size)
scores = torch.matmul(q, k.transpose(-1, -2)) / scale
if key_padding_mask is not None:
scores = scores.masked_fill(key_padding_mask[:, None, None, :], float("-inf"))
probs = F.softmax(scores, dim=-1)
probs = self.dropout(probs)
context = torch.matmul(probs, v)
B, _, T, _ = context.shape
context = context.permute(0, 2, 1, 3).contiguous().view(B, T, self.all_head_size)
if output_attentions:
return context, probs
return context, None
class BertSdpaSelfAttention(BertSelfAttention):
def forward(
self,
hidden_states: torch.Tensor,
key_padding_mask: Optional[torch.Tensor] = None,
output_attentions: bool = False,
) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
if output_attentions:
return super().forward(hidden_states, key_padding_mask, output_attentions=True)
B, T, _ = hidden_states.shape
q = self._split_heads(self.query(hidden_states))
k = self._split_heads(self.key(hidden_states))
v = self._split_heads(self.value(hidden_states))
attn_mask = None
if key_padding_mask is not None:
attn_mask = torch.zeros(B, 1, 1, T, dtype=q.dtype, device=q.device)
attn_mask = attn_mask.masked_fill(key_padding_mask[:, None, None, :], float("-inf"))
context = F.scaled_dot_product_attention(q, k, v, attn_mask=attn_mask)
context = context.permute(0, 2, 1, 3).contiguous().view(B, T, self.all_head_size)
return context, None
class BertFlashSelfAttention(BertSelfAttention):
def forward(
self,
hidden_states: torch.Tensor,
key_padding_mask: Optional[torch.Tensor] = None,
output_attentions: bool = False,
) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
if output_attentions:
return super().forward(hidden_states, key_padding_mask, output_attentions=True)
try:
from flash_attn import flash_attn_func, flash_attn_varlen_func
from flash_attn.bert_padding import pad_input, unpad_input
except ImportError as e:
raise ImportError(
"flash_attn is required for attn_implementation='flash_attention_2'. "
"Install with: pip install flash-attn --no-build-isolation"
) from e
B, T, _ = hidden_states.shape
q = self._split_heads(self.query(hidden_states)).permute(0, 2, 1, 3)
k = self._split_heads(self.key(hidden_states)).permute(0, 2, 1, 3)
v = self._split_heads(self.value(hidden_states)).permute(0, 2, 1, 3)
orig_dtype = q.dtype
if orig_dtype not in (torch.float16, torch.bfloat16):
q, k, v = q.to(torch.bfloat16), k.to(torch.bfloat16), v.to(torch.bfloat16)
if key_padding_mask is not None and key_padding_mask.any():
attend = ~key_padding_mask
q_u, indices, cu_seqlens, max_seqlen, _ = unpad_input(q, attend)
k_u, _, _, _, _ = unpad_input(k, attend)
v_u, _, _, _, _ = unpad_input(v, attend)
out_u = flash_attn_varlen_func(
q_u, k_u, v_u,
cu_seqlens_q=cu_seqlens, cu_seqlens_k=cu_seqlens,
max_seqlen_q=max_seqlen, max_seqlen_k=max_seqlen,
causal=False,
)
out = pad_input(out_u, indices, B, T)
else:
out = flash_attn_func(q, k, v, causal=False)
out = out.to(orig_dtype).reshape(B, T, self.all_head_size)
return out, None
BERT_SELF_ATTENTION_CLASSES = {
"eager": BertSelfAttention,
"sdpa": BertSdpaSelfAttention,
"flash_attention_2": BertFlashSelfAttention,
}
class BertSelfOutput(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
hidden_states = self.dropout(self.dense(hidden_states))
return self.LayerNorm(hidden_states + input_tensor)
class BertAttention(nn.Module):
def __init__(self, config):
super().__init__()
attn_cls = BERT_SELF_ATTENTION_CLASSES[getattr(config, "_attn_implementation", "eager")]
self.self = attn_cls(config)
self.output = BertSelfOutput(config)
def forward(
self,
hidden_states: torch.Tensor,
key_padding_mask: Optional[torch.Tensor],
output_attentions: bool = False,
) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
self_out, attn_weights = self.self(hidden_states, key_padding_mask, output_attentions)
return self.output(self_out, hidden_states), attn_weights
class BertIntermediate(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.intermediate_size)
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
return F.gelu(self.dense(hidden_states))
class BertOutput(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.intermediate_size, config.hidden_size)
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
hidden_states = self.dropout(self.dense(hidden_states))
return self.LayerNorm(hidden_states + input_tensor)
class BertLayer(nn.Module):
def __init__(self, config):
super().__init__()
self.attention = BertAttention(config)
self.intermediate = BertIntermediate(config)
self.output = BertOutput(config)
def forward(
self,
hidden_states: torch.Tensor,
key_padding_mask: Optional[torch.Tensor],
output_attentions: bool = False,
) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
attn_out, attn_weights = self.attention(hidden_states, key_padding_mask, output_attentions)
return self.output(self.intermediate(attn_out), attn_out), attn_weights
class BertEncoder(nn.Module):
def __init__(self, config):
super().__init__()
self.layer = nn.ModuleList([BertLayer(config) for _ in range(config.num_hidden_layers)])
def forward(
self,
hidden_states: torch.Tensor,
key_padding_mask: Optional[torch.Tensor],
output_hidden_states: bool = False,
output_attentions: bool = False,
) -> Tuple:
all_hidden_states = (hidden_states,) if output_hidden_states else None
all_attentions = () if output_attentions else None
for layer in self.layer:
hidden_states, attn_weights = layer(hidden_states, key_padding_mask, output_attentions)
if output_hidden_states:
all_hidden_states = all_hidden_states + (hidden_states,)
if output_attentions:
all_attentions = all_attentions + (attn_weights,)
return hidden_states, all_hidden_states, all_attentions
class BertEmbeddings(nn.Module):
def __init__(self, config):
super().__init__()
self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id)
self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.register_buffer("position_ids", torch.arange(config.max_position_embeddings).expand((1, -1)), persistent=False)
def forward(self, input_ids: torch.LongTensor, token_type_ids: Optional[torch.LongTensor] = None) -> torch.Tensor:
B, T = input_ids.shape
if token_type_ids is None:
token_type_ids = torch.zeros_like(input_ids)
x = self.word_embeddings(input_ids)
x = x + self.position_embeddings(self.position_ids[:, :T])
x = x + self.token_type_embeddings(token_type_ids)
return self.dropout(self.LayerNorm(x))
class BertPooler(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
self.activation = nn.Tanh()
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
return self.activation(self.dense(hidden_states[:, 0]))
class BertPredictionHeadTransform(nn.Module):
def __init__(self, config):
super().__init__()
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
return self.LayerNorm(F.gelu(self.dense(hidden_states)))
class BertModel(PreTrainedModel):
config_class = BertUpdatedConfig
base_model_prefix = "bert"
_supports_sdpa = True
_supports_flash_attn_2 = True
def __init__(self, config):
super().__init__(config)
self.embeddings = BertEmbeddings(config)
self.encoder = BertEncoder(config)
self.pooler = BertPooler(config)
self.post_init()
def get_input_embeddings(self):
return self.embeddings.word_embeddings
def set_input_embeddings(self, value):
self.embeddings.word_embeddings = value
def forward(
self,
input_ids: torch.LongTensor,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
output_hidden_states: Optional[bool] = None,
output_attentions: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutputWithPooling]:
output_hidden_states = output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
if attention_mask is None:
attention_mask = torch.ones_like(input_ids)
key_padding_mask = attention_mask.eq(0)
if not key_padding_mask.any():
key_padding_mask = None
x = self.embeddings(input_ids, token_type_ids)
last_hidden_state, all_hidden_states, all_attentions = self.encoder(
x, key_padding_mask,
output_hidden_states=output_hidden_states,
output_attentions=output_attentions,
)
pooled = self.pooler(last_hidden_state)
if not return_dict:
return tuple(v for v in [last_hidden_state, pooled, all_hidden_states, all_attentions] if v is not None)
return BaseModelOutputWithPooling(
last_hidden_state=last_hidden_state,
pooler_output=pooled,
hidden_states=all_hidden_states,
attentions=all_attentions,
)
class BertForMaskedLM(PreTrainedModel):
config_class = BertUpdatedConfig
base_model_prefix = "bert"
_supports_sdpa = True
_supports_flash_attn_2 = True
def __init__(self, config):
super().__init__(config)
self.bert = BertModel(config)
self.transform = BertPredictionHeadTransform(config)
self.cls = nn.Linear(config.hidden_size, config.vocab_size)
self.post_init()
def get_input_embeddings(self):
return self.bert.embeddings.word_embeddings
def forward(
self,
input_ids: torch.LongTensor,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.LongTensor] = None,
labels: Optional[torch.LongTensor] = None,
output_hidden_states: Optional[bool] = None,
output_attentions: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, MaskedLMOutput]:
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.bert(
input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids,
output_hidden_states=output_hidden_states, output_attentions=output_attentions,
return_dict=True,
)
logits = self.cls(self.transform(outputs.last_hidden_state))
loss = None
if labels is not None:
loss = F.cross_entropy(logits.view(-1, self.config.vocab_size), labels.view(-1), ignore_index=-100)
if not return_dict:
output = (logits,) + outputs[2:]
return (loss,) + output if loss is not None else output
return MaskedLMOutput(
loss=loss, logits=logits,
hidden_states=outputs.hidden_states, attentions=outputs.attentions,
)
|