Port Rotary Positional Embedding from NeuralAttentionlib.jl #2524
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Why did you close this? It would make sense to have it. Actually you could file a PR to NNlib with the function generating the rotatory embedding. |
|
Because it might not work on GPU and I figured I want to rewrite it not to compute rotations on fly but cache them. |
|
This is in a package now |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is pretty much standard thing to do these days with MultiHeadAttention layer, I think we should have it as part of Flux.
If anyone can review it, I would be happy. Too often I miss this.