support for rotary positional encoding to transformer modules. #1604
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
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #1604 /- ##
==========================================
- Coverage 86.39% 86.33% -0.07%
==========================================
Files 688 691 3
Lines 78676 79368 692
==========================================
Hits 67974 68520 546
- Misses 10702 10848 146 ☔ View full report in Codecov by Sentry. |
dcvz
reviewed
Apr 12, 2024
louisfd
approved these changes
Apr 12, 2024
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Outdated suggestions cannot be applied.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.
Pull Request Template
Checklist
run-checks allscript has been executed.Related Issues/PRs
#1603
Changes
Implementation of Rotary positional encodings as an alternative to sinusoidal positional embeddings due to their ability to incorporate explicit relative position dependency. They are being used in recent LLM models such as Llama, Mistral etc.
Testing
Test cases to verify output against PyTorch implementations of Rotary embeddings (https://github.com/lucidrains/rotary-embedding-torch).