File size: 4,611 Bytes
fdb5676 | 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 | """
Shared model utilities: sinusoidal embeddings, activation functions, blocks.
"""
import math
import torch
import torch.nn as nn
import torch.nn.functional as F
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Activations
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class Mish(nn.Module):
"""Mish activation: x * tanh(softplus(x))."""
def forward(self, x: torch.Tensor) -> torch.Tensor:
return x * torch.tanh(F.softplus(x))
class GEGLU(nn.Module):
"""Gated GELU activation for feedforward blocks."""
def forward(self, x: torch.Tensor) -> torch.Tensor:
x, gate = x.chunk(2, dim=-1)
return x * F.gelu(gate)
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Sinusoidal positional / time embedding
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class SinusoidalTimeEmbedding(nn.Module):
"""
Maps scalar timesteps to sinusoidal embeddings.
Args:
dim: output embedding dimension (must be even)
max_period: controls frequency range
"""
def __init__(self, dim: int, max_period: int = 10000):
super().__init__()
assert dim % 2 == 0, "dim must be even"
self.dim = dim
self.max_period = max_period
def forward(self, t: torch.Tensor) -> torch.Tensor:
"""
Args:
t: (B,) integer or float timesteps
Returns:
(B, dim) sinusoidal embeddings
"""
half = self.dim // 2
freqs = torch.exp(
-math.log(self.max_period)
* torch.arange(half, device=t.device, dtype=torch.float32)
/ half
)
args = t[:, None].float() * freqs[None, :]
return torch.cat([args.sin(), args.cos()], dim=-1)
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Building blocks
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
class FeedForward(nn.Module):
"""
Transformer feedforward block with GEGLU gating.
Args:
dim: input/output dimension
mult: hidden dimension multiplier
dropout: dropout rate
"""
def __init__(self, dim: int, mult: int = 4, dropout: float = 0.1):
super().__init__()
inner_dim = dim * mult * 2 # Γ2 for GEGLU split
self.net = nn.Sequential(
nn.LayerNorm(dim),
nn.Linear(dim, inner_dim),
GEGLU(),
nn.Dropout(dropout),
nn.Linear(dim * mult, dim),
nn.Dropout(dropout),
)
def forward(self, x: torch.Tensor) -> torch.Tensor:
return self.net(x)
class AdaLayerNorm(nn.Module):
"""
Adaptive Layer Normalization conditioned on time embedding.
Applies scale/shift modulation: Ξ³(t) * LayerNorm(x) + Ξ²(t)
Args:
dim: feature dimension
cond_dim: conditioning (time) embedding dimension
"""
def __init__(self, dim: int, cond_dim: int):
super().__init__()
self.norm = nn.LayerNorm(dim, elementwise_affine=False)
self.proj = nn.Sequential(
Mish(),
nn.Linear(cond_dim, dim * 2),
)
def forward(self, x: torch.Tensor, cond: torch.Tensor) -> torch.Tensor:
"""
Args:
x: (B, L, D) or (B, D)
cond: (B, cond_dim)
"""
gamma, beta = self.proj(cond).chunk(2, dim=-1)
if x.dim() == 3 and gamma.dim() == 2:
gamma = gamma.unsqueeze(1)
beta = beta.unsqueeze(1)
return self.norm(x) * (1 + gamma) + beta
|