Added max sample length filter to unlearning and retaining datasets #156
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
Signed-off-by: TheRootOf3 <aceszablewski@gmail.com>
Signed-off-by: Szymon Duchniewicz <szymon.duchniewicz.20@ucl.ac.uk>
…tructor. Signed-off-by: Szymon Duchniewicz <szymon.duchniewicz.20@ucl.ac.uk>
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Outdated suggestions cannot be applied.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.
Added a way to set the maximum sample length (in tokens) for both the unlearning and retaining datasets. This was implemented to limit the GPU memory usage on longer samples.
This change introduces another argument to the
unlearn_harm.pyscript:max_sample_length, which represents the maximum number of tokens (after adding the prompt) of a sample. Essentially, this will be the maximum dimension of a tensor that goes through the model.