File size: 13,113 Bytes
967e04b |
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 |
"""MagicBERT model implementation for HuggingFace transformers.
This module provides HuggingFace-compatible implementations of MagicBERT,
a BERT-style model trained for binary file type understanding.
"""
import math
from dataclasses import dataclass
from typing import Optional, Tuple, Union
import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers import PreTrainedModel
from transformers.modeling_outputs import (
MaskedLMOutput,
SequenceClassifierOutput,
BaseModelOutput,
)
try:
from .configuration_magic_bert import MagicBERTConfig
except ImportError:
from configuration_magic_bert import MagicBERTConfig
class MagicBERTEmbeddings(nn.Module):
"""MagicBERT embeddings: token + position embeddings."""
def __init__(self, config: MagicBERTConfig):
super().__init__()
self.token_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.layer_norm = 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.Tensor) -> torch.Tensor:
batch_size, seq_length = input_ids.shape
token_embeds = self.token_embeddings(input_ids)
position_ids = self.position_ids[:, :seq_length]
position_embeds = self.position_embeddings(position_ids)
embeddings = token_embeds + position_embeds
embeddings = self.layer_norm(embeddings)
embeddings = self.dropout(embeddings)
return embeddings
class MagicBERTAttention(nn.Module):
"""Multi-head self-attention."""
def __init__(self, config: MagicBERTConfig):
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 transpose_for_scores(self, x: torch.Tensor) -> torch.Tensor:
new_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size)
x = x.view(new_shape)
return x.permute(0, 2, 1, 3)
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
query_layer = self.transpose_for_scores(self.query(hidden_states))
key_layer = self.transpose_for_scores(self.key(hidden_states))
value_layer = self.transpose_for_scores(self.value(hidden_states))
attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
attention_scores = attention_scores / math.sqrt(self.attention_head_size)
if attention_mask is not None:
attention_mask = attention_mask[:, None, None, :]
attention_scores = attention_scores + (1.0 - attention_mask) * -10000.0
attention_probs = F.softmax(attention_scores, dim=-1)
attention_probs = self.dropout(attention_probs)
context = torch.matmul(attention_probs, value_layer)
context = context.permute(0, 2, 1, 3).contiguous()
new_shape = context.size()[:-2] + (self.all_head_size,)
context = context.view(new_shape)
return context
class MagicBERTLayer(nn.Module):
"""Single transformer layer."""
def __init__(self, config: MagicBERTConfig):
super().__init__()
self.attention = MagicBERTAttention(config)
self.attention_output = nn.Linear(config.hidden_size, config.hidden_size)
self.attention_norm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.attention_dropout = nn.Dropout(config.hidden_dropout_prob)
self.intermediate = nn.Linear(config.hidden_size, config.intermediate_size)
self.output = nn.Linear(config.intermediate_size, config.hidden_size)
self.output_norm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
self.output_dropout = nn.Dropout(config.hidden_dropout_prob)
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
# Self-attention with residual
attention_output = self.attention(hidden_states, attention_mask)
attention_output = self.attention_output(attention_output)
attention_output = self.attention_dropout(attention_output)
attention_output = self.attention_norm(hidden_states + attention_output)
# Feed-forward with residual
intermediate_output = self.intermediate(attention_output)
intermediate_output = F.gelu(intermediate_output)
layer_output = self.output(intermediate_output)
layer_output = self.output_dropout(layer_output)
layer_output = self.output_norm(attention_output + layer_output)
return layer_output
class MagicBERTEncoder(nn.Module):
"""Stack of transformer layers."""
def __init__(self, config: MagicBERTConfig):
super().__init__()
self.layers = nn.ModuleList(
[MagicBERTLayer(config) for _ in range(config.num_hidden_layers)]
)
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
for layer in self.layers:
hidden_states = layer(hidden_states, attention_mask)
return hidden_states
class MagicBERTPreTrainedModel(PreTrainedModel):
"""Base class for MagicBERT models."""
config_class = MagicBERTConfig
base_model_prefix = "magic_bert"
supports_gradient_checkpointing = False
def _init_weights(self, module):
if isinstance(module, nn.Linear):
module.weight.data.normal_(mean=0.0, std=0.02)
if module.bias is not None:
module.bias.data.zero_()
elif isinstance(module, nn.Embedding):
module.weight.data.normal_(mean=0.0, std=0.02)
if module.padding_idx is not None:
module.weight.data[module.padding_idx].zero_()
elif isinstance(module, nn.LayerNorm):
module.bias.data.zero_()
module.weight.data.fill_(1.0)
class MagicBERTModel(MagicBERTPreTrainedModel):
"""MagicBERT base model outputting raw hidden states."""
def __init__(self, config: MagicBERTConfig):
super().__init__(config)
self.config = config
self.embeddings = MagicBERTEmbeddings(config)
self.encoder = MagicBERTEncoder(config)
self.post_init()
def forward(
self,
input_ids: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.Tensor] = None, # Ignored, for tokenizer compatibility
return_dict: Optional[bool] = None,
) -> Union[Tuple[torch.Tensor, torch.Tensor], BaseModelOutput]:
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
hidden_states = self.embeddings(input_ids)
sequence_output = self.encoder(hidden_states, attention_mask)
pooled_output = sequence_output[:, 0, :]
if not return_dict:
return (sequence_output, pooled_output)
return BaseModelOutput(
last_hidden_state=sequence_output,
hidden_states=None,
attentions=None,
)
class MagicBERTForMaskedLM(MagicBERTPreTrainedModel):
"""MagicBERT for masked language modeling (fill-mask task)."""
def __init__(self, config: MagicBERTConfig):
super().__init__(config)
self.config = config
self.embeddings = MagicBERTEmbeddings(config)
self.encoder = MagicBERTEncoder(config)
self.mlm_head = nn.Linear(config.hidden_size, config.vocab_size)
self.post_init()
def forward(
self,
input_ids: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.Tensor] = None, # Ignored, for tokenizer compatibility
labels: Optional[torch.Tensor] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple[torch.Tensor, ...], MaskedLMOutput]:
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
hidden_states = self.embeddings(input_ids)
sequence_output = self.encoder(hidden_states, attention_mask)
logits = self.mlm_head(sequence_output)
loss = None
if labels is not None:
loss_fct = nn.CrossEntropyLoss(ignore_index=-100)
loss = loss_fct(logits.view(-1, self.config.vocab_size), labels.view(-1))
if not return_dict:
output = (logits,)
return ((loss,) + output) if loss is not None else output
return MaskedLMOutput(
loss=loss,
logits=logits,
hidden_states=None,
attentions=None,
)
def get_embeddings(
self,
input_ids: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
pooling: str = "cls",
) -> torch.Tensor:
"""Get embeddings for downstream tasks.
Args:
input_ids: Input token IDs
attention_mask: Attention mask
pooling: Pooling strategy ("cls" or "mean")
Returns:
Pooled embeddings [batch_size, hidden_size]
"""
hidden_states = self.embeddings(input_ids)
sequence_output = self.encoder(hidden_states, attention_mask)
if pooling == "cls":
return sequence_output[:, 0, :]
elif pooling == "mean":
if attention_mask is not None:
mask = attention_mask.unsqueeze(-1).float()
return (sequence_output * mask).sum(1) / mask.sum(1).clamp(min=1e-9)
return sequence_output.mean(dim=1)
else:
raise ValueError(f"Unknown pooling: {pooling}")
class MagicBERTForSequenceClassification(MagicBERTPreTrainedModel):
"""MagicBERT for sequence classification (file type classification)."""
def __init__(self, config: MagicBERTConfig):
super().__init__(config)
self.config = config
self.num_labels = getattr(config, "num_labels", 106)
self.embeddings = MagicBERTEmbeddings(config)
self.encoder = MagicBERTEncoder(config)
# Projection head (for contrastive learning compatibility)
projection_dim = getattr(config, "contrastive_projection_dim", 256)
self.projection = nn.Sequential(
nn.Linear(config.hidden_size, config.hidden_size),
nn.ReLU(),
nn.Linear(config.hidden_size, projection_dim),
)
self.classifier = nn.Linear(projection_dim, self.num_labels)
self.post_init()
def forward(
self,
input_ids: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
token_type_ids: Optional[torch.Tensor] = None, # Ignored, for tokenizer compatibility
labels: Optional[torch.Tensor] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple[torch.Tensor, ...], SequenceClassifierOutput]:
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
hidden_states = self.embeddings(input_ids)
sequence_output = self.encoder(hidden_states, attention_mask)
pooled_output = sequence_output[:, 0, :]
projections = self.projection(pooled_output)
projections = F.normalize(projections, p=2, dim=1)
logits = self.classifier(projections)
loss = None
if labels is not None:
loss_fct = nn.CrossEntropyLoss()
loss = loss_fct(logits, labels)
if not return_dict:
output = (logits,)
return ((loss,) + output) if loss is not None else output
return SequenceClassifierOutput(
loss=loss,
logits=logits,
hidden_states=None,
attentions=None,
)
def get_embeddings(
self,
input_ids: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
"""Get normalized projection embeddings for similarity search."""
hidden_states = self.embeddings(input_ids)
sequence_output = self.encoder(hidden_states, attention_mask)
pooled_output = sequence_output[:, 0, :]
projections = self.projection(pooled_output)
return F.normalize(projections, p=2, dim=1)
|