Ensure attn_norm does not affect the residual stream #680
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Outdated suggestions cannot be applied.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.
Issue: The attention norm, when applied before the attention block, was modifying the residual stream. This was introduced in aac4bdd.
Fix: Ensure the attention norm does not modify the residual stream.
Testing: I used a script to check that this PR made the output match that from https://github.com/allenai/OLMo/tree/ladder-1xC, which is healthy according to @AkshitaB. Before the fix, the outputs (and inputs) would start disagreeing at the feed forward norm.