1 write to query
Microsoft.ML.TorchSharp (1)
Roberta\Modules\AttentionSelf.cs (1)
37
query
= torch.nn.Linear(hiddenSize, hiddenSize, true);
2 references to query
Microsoft.ML.TorchSharp (2)
Roberta\Modules\AttentionSelf.cs (2)
48
var mixedQueryLayer =
query
.forward(hiddenStates);
92
query
.Dispose();