-
Notifications
You must be signed in to change notification settings - Fork 12
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Remove 0.5 code #743
Remove 0.5 code #743
Conversation
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍🏻
@@ -5,9 +5,9 @@ | |||
import pytest | |||
|
|||
from modelbench.benchmarks import BenchmarkScore, GeneralPurposeAiChatBenchmarkV1, Locale | |||
from modelbench.hazards import HazardScore, SafeCaeHazard, SafeCbrHazard, SafeHatHazard, Standards | |||
from modelbench.hazards import HazardScore, SafeHazardV1, Standards |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do you know the original motivation for having one individual subclass for each hazard?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No, I don't
* SUT arg(s) is now required by CLI * Get rid of DEFFAULT_SUTS * mb tests use centralized SUT fixtures * mv conftest up to root tests dir * Modelbench does not register SUTs * print known SUT uids on newlines * Remove SUT wrapper (#758)
Merge PR #747 before this one.
Notes:
Record is now dumped in
run/records
instead ofweb
. This might require a corresponding change in modellab.The CLI now prints out a table summary in place of a static site. Let me know if it is missing any useful benchmark data.
We should consider what we want to do about static content. If we want to keep it here, we will need to add tests to make sure that static content for the relevant objects expected my modellab indeed exists. This would avoid the numerous issues we've run into in the past w.r.t. uid changes not syncing up with the content.