Hi, @leaderj1001
Thanks for your code. However, I am a little bit confused about this line
|
lambda_p = torch.einsum('ku,bvun->bkvn', self.embedding, values) |
It seems like did not use relative position embedding when strategy is not local context. What's the meaning of this line?
Hi, @leaderj1001
Thanks for your code. However, I am a little bit confused about this line
LambdaNetworks/model.py
Line 48 in 3a51b6a
It seems like did not use relative position embedding when strategy is not local context. What's the meaning of this line?