SwiGLU
feed_forward.SwiGLU
https://arxiv.org/abs/2002.05202 NOTE: x should be 2x the size you want
forward(self, x: torch.Tensor) -> torch.Tensor
(undocumented)
| Parameter | Type | Default | Description |
|---|---|---|---|
| x | torch.Tensor | - | (undocumented) |