(self, hidden_states)
| 40 | ) |
| 41 | |
| 42 | def forward(self, hidden_states): |
| 43 | # [s, b, 4hp] |
| 44 | intermediate_parallel = self.dense_h_to_4h(hidden_states) |
| 45 | intermediate_parallel = self.activation_func(intermediate_parallel) |
| 46 | # [s, b, h] |
| 47 | output = self.dense_4h_to_h(intermediate_parallel) |
| 48 | |
| 49 | return output |
| 50 | |
| 51 | |
| 52 | class SelfAttention(torch.nn.Module): |
nothing calls this directly
no outgoing calls
no test coverage detected