FEAT Add adversarial suffix attack GCG #180
Open
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
romanlutz
reviewed
Apr 29, 2024
| del control_cands, loss | ||
| gc.collect() | ||
|
|
||
| print("Current length:", len(self.workers[0].tokenizer(next_control).input_ids[1:])) |
There was a problem hiding this comment.
Not urgent, but eventually we'd want to use the logger the same way we do elsewhere in the repo. That way, you can specify the desired log level and only see the corresponding output.
|
FYI #192 (comment) |
… files to read from YAML.
NaijingGuo
changed the title
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Outdated suggestions cannot be applied.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.
Description
Optimizer for adversarial suffix using GCG.
suffix attack from https://arxiv.org/pdf/2307.15043.pdf
Tests and Documentation
TODO:
Tests and documentation to be added.