Skip to content

FEAT Add ability to fetch wmdp-bio, wmdp-chem, and wmdp-cyber datasets#380

Merged
romanlutz merged 54 commits into
microsoft:mainfrom
mshirsekar1:FHL/add-wmdp-dataset
Sep 18, 2024
Merged

FEAT Add ability to fetch wmdp-bio, wmdp-chem, and wmdp-cyber datasets#380
romanlutz merged 54 commits into
microsoft:mainfrom
mshirsekar1:FHL/add-wmdp-dataset

Conversation

@mshirsekar1
Copy link
Copy Markdown
Contributor

Description

Add the ability to fetch the wmdp-bio, wmdp-chem, and wmdp-cyber datasets from Hugging Face. This is related to issue https://github.com/Azure/PyRIT/issues/186

Tests and Documentation

Test ability to fetch the dataset from Hugging Face, and validated the QuestionAnsweringDataset format can be used as prompts successfully

mshirsekar1 and others added 30 commits September 16, 2024 11:54
FEAT add ability to fetch PKU-SafeRLHF dataset
Co-authored-by: Roman Lutz <romanlutz13@gmail.com>
Co-authored-by: Roman Lutz <romanlutz13@gmail.com>
Co-authored-by: Roman Lutz <romanlutz13@gmail.com>
Co-authored-by: Roman Lutz <romanlutz13@gmail.com>
@mshirsekar1
Copy link
Copy Markdown
Contributor Author

@microsoft-github-policy-service agree company="Microsoft"

@romanlutz
Copy link
Copy Markdown
Contributor

Amazing! Thank you so much for tackling this!

Can you remove the existing WMDP datasets that are stored in the repo?

@romanlutz romanlutz linked an issue Sep 18, 2024 that may be closed by this pull request
Comment thread doc/code/orchestrators/benchmark_orchestrator.ipynb
Comment thread pyrit/datasets/fetch_example_datasets.py Outdated
Comment thread pyrit/datasets/fetch_example_datasets.py Outdated
@mshirsekar1 mshirsekar1 marked this pull request as ready for review September 18, 2024 22:25
Comment thread pyrit/datasets/fetch_example_datasets.py Outdated
Comment thread pyrit/datasets/fetch_example_datasets.py
Comment thread pyrit/datasets/fetch_example_datasets.py Outdated
@romanlutz romanlutz merged commit 88c8872 into microsoft:main Sep 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Update WMDP Dataset

3 participants