Spaces:
Paused
Paused
import torch | |
from torch import nn | |
import torch.nn.functional as F | |
class GEGLU(nn.Module): | |
def __init__(self, dim_in, dim_out): | |
super().__init__() | |
self.proj = nn.Linear(dim_in, dim_out * 2) | |
def forward(self, x): | |
x, gate = self.proj(x).chunk(2, dim=-1) | |
return x * F.gelu(gate) | |
class FeedForward(nn.Module): | |
def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.): | |
super().__init__() | |
inner_dim = int(dim * mult) | |
dim_out = dim_out or dim | |
project_in = nn.Sequential( | |
nn.Linear(dim, inner_dim), | |
nn.GELU() | |
) if not glu else GEGLU(dim, inner_dim) | |
self.net = nn.Sequential( | |
project_in, | |
nn.Dropout(dropout), | |
nn.Linear(inner_dim, dim_out) | |
) | |
def forward(self, x): | |
return self.net(x) |