File size: 10,182 Bytes
a10898b 1085007 a10898b 63fe031 a10898b 1085007 a10898b 1085007 a10898b 1085007 a10898b 63fe031 a10898b 1085007 a10898b 1085007 a10898b 1085007 a10898b b0c4b27 | 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 | import torch
import torch.nn as nn
import torch.nn.functional as F
from .rope_embeddings import RotaryEmbedding
from transformers import PreTrainedModel, AutoConfig, AutoModelForSequenceClassification
from transformers.modeling_outputs import SequenceClassifierOutput
from .configuration_emcoder import EmCoderConfig
class RMSNorm(nn.Module):
def __init__(self, dim: int, eps: float = 1e-6):
super().__init__()
self.eps = eps
self.weight = nn.Parameter(torch.ones(dim))
def forward(self, x: torch.Tensor) -> torch.Tensor:
variance = x.pow(2).mean(-1, keepdim=True)
return x * torch.rsqrt(variance + self.eps) * self.weight
class SwiGLU(nn.Module):
def __init__(self, d_model: int, d_ffn: int):
super().__init__()
self.wi = nn.Linear(d_model, 2 * d_ffn, bias=False)
self.wo = nn.Linear(d_ffn, d_model, bias=False)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x1, x2 = self.wi(x).chunk(2, dim=-1)
return self.wo(x1 * F.silu(x2))
class EmCoderEncoderLayer(nn.Module):
"""Custom Pre-LN Transformer Encoder Layer with RoPE and FlashAttention."""
def __init__(self, config: EmCoderConfig, rope: RotaryEmbedding):
super().__init__()
self.n_head = config.n_head
self.d_head = config.d_model // config.n_head
self.rope = rope
# Attention projections
self.q_proj = nn.Linear(config.d_model, config.d_model, bias=False)
self.k_proj = nn.Linear(config.d_model, config.d_model, bias=False)
self.v_proj = nn.Linear(config.d_model, config.d_model, bias=False)
self.out_proj = nn.Linear(config.d_model, config.d_model, bias=False)
self.ln1 = RMSNorm(config.d_model)
self.ln2 = RMSNorm(config.d_model)
self.ffn = SwiGLU(config.d_model, config.d_ffn)
self.dropout = nn.Dropout(config.dropout)
# mark for initialization
self.out_proj._is_residual = True
self.ffn.wo._is_residual = True
def forward(self, x: torch.Tensor, attn_mask: torch.Tensor) -> torch.Tensor:
# MULTI-HEAD ATTENTION
residual = x
nx = self.ln1(x)
B, S, _ = nx.shape
# Projections -> (B, H, S, D_head)
q = self.q_proj(nx).view(B, S, self.n_head, self.d_head).transpose(1, 2)
k = self.k_proj(nx).view(B, S, self.n_head, self.d_head).transpose(1, 2)
v = self.v_proj(nx).view(B, S, self.n_head, self.d_head).transpose(1, 2)
q = self.rope.rotate_queries_or_keys(q)
k = self.rope.rotate_queries_or_keys(k)
attn_out = F.scaled_dot_product_attention(
q,
k,
v,
attn_mask=attn_mask,
dropout_p=self.dropout.p if self.dropout.training else 0.0,
)
# Join heads -> (B, S, D_model)
attn_out = attn_out.transpose(1, 2).contiguous().view(B, S, -1)
x = residual + self.dropout(self.out_proj(attn_out))
x = x + self.dropout(self.ffn(self.ln2(x)))
return x
class EmCoderEncoder(nn.Module):
"""The core encoder architecture of EmCoder Transformer."""
def __init__(self, config: EmCoderConfig):
super().__init__()
self.token_embedding = nn.Embedding(config.vocab_size, config.d_model)
self.embed_norm = RMSNorm(config.d_model)
self.dropout = nn.Dropout(config.dropout)
self.rope = RotaryEmbedding(dim=config.d_model // config.n_head)
self.layers = nn.ModuleList(
[EmCoderEncoderLayer(config, self.rope) for _ in range(config.n_layers)]
)
self.final_norm = RMSNorm(config.d_model)
def forward(self, x: torch.Tensor, mask: torch.Tensor) -> torch.Tensor:
"""Standard forward pass through the encoder."""
x = self.token_embedding(x)
x = self.embed_norm(x)
x = self.dropout(x)
B, S = mask.shape
attn_mask = mask.view(B, 1, 1, S).to(dtype=torch.bool)
for layer in self.layers:
x = layer(x, attn_mask)
return self.final_norm(x)
class EmCoder(PreTrainedModel):
"""The full EmCoder model, including the backbone encoder and the classification head."""
config_class = EmCoderConfig
def __init__(self, config: EmCoderConfig):
super().__init__(config)
self.encoder = EmCoderEncoder(config)
self.classifier = nn.Sequential(
nn.Linear(config.d_model, config.d_model),
nn.GELU(),
nn.Dropout(config.dropout),
nn.Linear(config.d_model, config.num_labels),
)
self.post_init()
def _init_weights(self, module: nn.Module) -> None:
if isinstance(module, nn.Linear):
# scale down the init for residual connections
if getattr(module, "_is_residual", False):
std = 0.02 / ((2 * self.config.n_layers) ** 0.5)
else:
std = 0.02
nn.init.trunc_normal_(module.weight, std=std)
if module.bias is not None:
nn.init.zeros_(module.bias)
elif isinstance(module, nn.Embedding):
nn.init.trunc_normal_(module.weight, std=0.02)
elif isinstance(module, RMSNorm):
nn.init.ones_(module.weight)
def _set_mc_dropout(self, active: bool = True):
for m in self.modules():
if isinstance(m, nn.Dropout):
m.train(active)
@staticmethod
def _masked_mean_pooling(
features: torch.Tensor, mask: torch.Tensor
) -> torch.Tensor:
mask = mask.unsqueeze(-1) # (B, S, 1)
masked_features = features * mask # (B, S, D)
sum_masked_features = masked_features.sum(dim=1) # (B, D)
count_tokens = torch.clamp(mask.sum(dim=1), min=1e-9) # (B, 1)
return sum_masked_features / count_tokens # (B, D)
def mc_forward(
self,
input_ids: torch.Tensor | None = None,
attention_mask: torch.Tensor | None = None,
labels: torch.Tensor | None = None,
n_samples: int = 10,
max_batch_size: int | None = None,
return_dict: bool | None = None,
**kwargs,
) -> tuple[torch.Tensor, ...] | SequenceClassifierOutput:
"""
Performs Monte Carlo Dropout inference to quantify uncertainty.
Args:
input_ids: Input token IDs of shape (B, S).
attention_mask: Attention mask of shape (B, S).
n_samples: Total number of Monte Carlo samples.
max_batch_size: Maximum number of samples in one forward pass.
Returns:
Logits of shape (n_samples, B, num_labels).
"""
return_dict = return_dict if return_dict is not None else True
x = input_ids if input_ids is not None else kwargs.get("input_ids")
mask = attention_mask if attention_mask is not None else kwargs.get("attention_mask")
if x is None or mask is None:
raise ValueError("input_ids and attention_mask must be provided")
if max_batch_size is None:
max_batch_size = n_samples
B, S = x.shape
num_labels = self.classifier[-1].out_features
all_logits = torch.empty((n_samples, B, num_labels), device=x.device)
is_training = self.training
self._set_mc_dropout(active=True)
try:
with torch.no_grad():
for i in range(0, n_samples, max_batch_size):
batch_samples = min(max_batch_size, n_samples - i)
x_stacked = x.repeat(batch_samples, 1) # (batch_samples * B, S)
mask_stacked = mask.repeat(batch_samples, 1) # (batch_samples * B, S)
features = self.encoder(
x_stacked, mask_stacked
) # (batch_samples * B, S, D)
pooled = self._masked_mean_pooling(features, mask_stacked)
logits = self.classifier(pooled) # (n_samples * B, num_labels)
all_logits[i : i + batch_samples] = logits.view(batch_samples, B, -1)
finally:
self._set_mc_dropout(active=is_training)
loss = None
if labels is not None:
loss_fct = nn.BCEWithLogitsLoss()
logits_mean = all_logits.mean(dim=0) # (B, num_labels)
target_labels = labels.to(dtype=all_logits.dtype).view(logits_mean.shape)
loss = loss_fct(logits_mean, target_labels)
if not return_dict:
output = (all_logits,)
return ((loss,) + output) if loss is not None else output
return SequenceClassifierOutput(
loss=loss,
logits=all_logits,
hidden_states=None,
attentions=None,
)
def forward(
self,
input_ids: torch.Tensor | None = None,
attention_mask: torch.Tensor | None = None,
labels: torch.Tensor | None = None,
return_dict: bool | None = None,
**kwargs,
) -> tuple[torch.Tensor, ...] | SequenceClassifierOutput:
"""Standard forward pass without MC Dropout."""
return_dict = return_dict if return_dict is not None else True
x = input_ids if input_ids is not None else kwargs.get("input_ids")
mask = attention_mask if attention_mask is not None else kwargs.get("attention_mask")
if x is None or mask is None:
raise ValueError("input_ids and attention_mask must be provided")
features = self.encoder(x, mask)
pooled = self._masked_mean_pooling(features, mask)
logits = self.classifier(pooled)
loss = None
if labels is not None:
loss_fct = nn.BCEWithLogitsLoss()
target_labels = labels.to(dtype=logits.dtype).view(logits.shape)
loss = loss_fct(logits, target_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,
) |