Added functionality of storing layers activations output.#145
Merged
copybara-service[bot] merged 3 commits intogoogle:devfrom Apr 12, 2024
Merged
Added functionality of storing layers activations output.#145copybara-service[bot] merged 3 commits intogoogle:devfrom
copybara-service[bot] merged 3 commits intogoogle:devfrom
Conversation
jan-wassenberg
approved these changes
Apr 12, 2024
Member
jan-wassenberg
left a comment
jan-wassenberg
left a comment
There was a problem hiding this comment.
Nice, thanks for updating the PR!
jan-wassenberg
added
the
copybara-import
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adding a way to save activations output after applying each layer. This can be useful for two purposes:
There will be a similar functionality in the Python code and a diffing tool that will compare two outputs and calculating some metrics for them. See the output of such a tool when comparing outputs of (3 tokens)x(27 layers) between the Python and the C++ (8-bit) Recurrent Gemma implementations: