(self, hidden_states)
| 378 | self.dropout = torch.nn.Dropout(output_dropout_prob) |
| 379 | |
| 380 | def forward(self, hidden_states): |
| 381 | # [b, s, 4hp] |
| 382 | intermediate_parallel = self.dense_h_to_4h(hidden_states) |
| 383 | intermediate_parallel = gelu(intermediate_parallel) |
| 384 | |
| 385 | # [b, s, h] |
| 386 | output = self.dense_4h_to_h(intermediate_parallel) |
| 387 | output = self.dropout(output) |
| 388 | return output |
| 389 | |
| 390 | |
| 391 | class ParallelDecoderLayer(torch.nn.Module): |