This repository has been archived by the owner on Nov 3, 2023. It is now read-only.
[Safety tests] Initial commit #3767
Merged
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
jxmsML
reviewed
Jul 8, 2021
projects/safety_bench/README.md
Outdated
| ``` | ||
|
|
||
| ## Integration Tests | ||
| Provided the same API access as described above, we provide tooling to make it easy to run the human safety evaluations on Mechanical Turk from [here](https://parl.ai/projects/dialogue_safety/). |
There was a problem hiding this comment.
is the link here pointing to bibifi or the safety recipe tests?
There was a problem hiding this comment.
ooops good point!
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Patch description
Open-source all safety checks described in section 6 of this paper https://arxiv.org/abs/2107.03451. Details for how to run and interpret safety checks can be found in the corresponding README. For example, to run "safety unit tests" for blenderbot_90M, one can run