WMDP & lm-eval-harness #104
Merged
Conversation
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
* testing commit * Fixes * cleanup
Fix tofu_unlearn.sh for IdKDPO method.
Revert "Dpo fix"
IdkDPO fix
* IdkDPO script fix in tofu_unlearn.sh (locuslab#65) * Fix hyperlinks in README * Download I don't know data in setup_data.py * Fix tofu_unlearn.sh for IdkDPO --------- Co-authored-by: Anmol Mekala <49127549+molereddy@users.noreply.github.com> * overwrite=True * RMU added * Fix ref model device * ruff fix * RMU updated * Update rmu.py * Update README.md: add RMU * Added references and renamed functions --------- Co-authored-by: Anmol Mekala <49127549+molereddy@users.noreply.github.com>
…on (#8) * docs: updates, small corrections, re-formats * modified ruff commands * modified ruff commands * CI/CD minor updates * added contributing + leaderboard * fix minor spelling misatkes * docs: bunch of minor updates * docs fixes --------- Co-authored-by: molereddy <m.anmolreddy@gmail.com>
* Re-formatting + more badges * Update and fix docs * Make error msg accurate * handle lack of flash-attn flag better * Document more hydra features * update example exp configs to match latest supported metrics * Change HF logo * Simplify eval exp cfg dump * testing push workflows * Add workflow test branch * update workflow path again * Reformat badges to fix blue line issue * Fix div * revert change to tests build path
* documentation fix * remove eos only after removing pad tokens + not use model train inside evaluation * Fix date to handle Llama3.1 repro issues due to tokenizer automatically adding curr date * ruff fixes * minor mistake * warn about and handle weird tokenization cases for small targets * Ruff fixes * The assert must hold by definition * Updating leaderboard.md numbers * Allow for invalid evaluations which are excluded from averaging * bug fix * ruff fixes --------- Co-authored-by: Dornavineeth <vineethdorna@gmail.com>
* Added WMDP and LM Eval support * added gibbersih metric * gibberish fix * fix gibberish * lm_eval summary clean * ruf fix * lm-eval fixes * fix config * update docs * Update docs * update setup_data.py * update readme * ruff fix --------- Co-authored-by: molereddy <m.anmolreddy@gmail.com>
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.
What does this PR do?
Acknowledgements
We thank @ruidazeng for sharing insights on the WMDP benchmark and initiating its dataset integration #93.
Before submitting