Clarify ambiguity in decoder self-attention vs cross-attention in seq2seq section - #1280
Open
E-HAZMATs wants to merge 1 commit into
Open
Clarify ambiguity in decoder self-attention vs cross-attention in seq2seq section#1280E-HAZMATs wants to merge 1 commit into
E-HAZMATs wants to merge 1 commit into
Conversation
…2seq section The previous phrasing implied a single "attention layers of the decoder" with one access pattern. In practice, self-attention (restricted to prior positions in the target sequence) and cross-attention (full access to the encoder's output) behave differently and should be described separately.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The previous phrasing implied a single "attention layers of the decoder" with one access pattern. In practice, self-attention (restricted to prior positions in the target sequence) and cross-attention (full access to the encoder's output) behave differently and should be described separately.