We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
In https://github.com/cybertronai/transformer-xl/blob/master/mem_transformer.py#L106 , I am wondering why only key and value are layernormed, while query is not normed? In other variants (such as RelMultiHeadAttn), the qkv computation is implemented by a single self.qkv_net layer.
key
value
query
if self.pre_lnorm: ##### layer normalization c = self.layer_norm(c) head_q = self.q_net(h) head_k, head_v = torch.chunk(self.kv_net(c), 2, -1)
The text was updated successfully, but these errors were encountered:
This part came directly from the original repo, you could ask on original repo -- https://github.com/kimiyoung/transformer-xl/issues
Sorry, something went wrong.
No branches or pull requests
In https://github.com/cybertronai/transformer-xl/blob/master/mem_transformer.py#L106 , I am wondering why only
key
andvalue
are layernormed, whilequery
is not normed? In other variants (such as RelMultiHeadAttn), the qkv computation is implemented by a single self.qkv_net layer.The text was updated successfully, but these errors were encountered: