core.activations#
Module Contents#
Functions#
Squared ReLU activation |
|
Tanh Soft Clamp to precondition activation inputs. |
|
Sigmoid-Tanh Unit from Kimi K3: |
|
SiTU-GLU: |
|
Quick GELU activation |
|
Fast GELU activation |
API#
- core.activations.squared_relu(x: torch.Tensor) torch.Tensor#
Squared ReLU activation
- core.activations.tanh_soft_clamp(x: torch.Tensor, scale: float) torch.Tensor#
Tanh Soft Clamp to precondition activation inputs.
- core.activations.situ(x: torch.Tensor, scale: float) torch.Tensor#
Sigmoid-Tanh Unit from Kimi K3:
s * tanh(x / s) * sigmoid(x)
- core.activations.situ_glu(
- x: torch.Tensor,
- gate_scale: float,
- linear_scale: Optional[float] = None,
- linear_offset: float = 0.0,
SiTU-GLU:
situ(x_gate, gate_scale) * (x_linear + linear_offset).
- core.activations.quick_gelu(x: torch.Tensor) torch.Tensor#
Quick GELU activation
- core.activations.fast_gelu(x: torch.Tensor) torch.Tensor#
Fast GELU activation