(
self,
hidden_size,
)
| 20 | """ |
| 21 | |
| 22 | def __init__( |
| 23 | self, |
| 24 | hidden_size, |
| 25 | ): |
| 26 | super(MLP, self).__init__() |
| 27 | self.hidden_size = hidden_size |
| 28 | # Project to 4h. |
| 29 | self.dense_h_to_4h = torch.nn.Linear( |
| 30 | self.hidden_size, |
| 31 | 4 * self.hidden_size, |
| 32 | ) |
| 33 | |
| 34 | self.activation_func = fast_gelu |
| 35 | |
| 36 | # Project back to h. |
| 37 | self.dense_4h_to_h = torch.nn.Linear( |
| 38 | 4 * self.hidden_size, |
| 39 | self.hidden_size, |
| 40 | ) |
| 41 | |
| 42 | def forward(self, hidden_states): |
| 43 | # [s, b, 4hp] |