Skip to content

Add evals with Inspect guide to Inference Providers#2036

Merged
Vaibhavs10 merged 10 commits intohuggingface:mainfrom
dvsrepo:inspect_ai_evals_guide
Nov 12, 2025
Merged

Add evals with Inspect guide to Inference Providers#2036
Vaibhavs10 merged 10 commits intohuggingface:mainfrom
dvsrepo:inspect_ai_evals_guide

Conversation

@dvsrepo
Copy link
Contributor

@dvsrepo dvsrepo commented Nov 4, 2025

No description provided.

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

Copy link
Member

@davanstrien davanstrien left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very nice! Love the example! Made a few small comments and nit suggestion for language (feel free to ignore!)

Copy link
Member

@pcuenca pcuenca left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very cool! 🔥

dvsrepo and others added 5 commits November 5, 2025 17:32
Co-authored-by: Daniel van Strien <davanstrien@users.noreply.github.com>
Co-authored-by: Daniel van Strien <davanstrien@users.noreply.github.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
@NathanHB
Copy link
Member

NathanHB commented Nov 6, 2025

great blog post ! Don't know if it's in scope of the blog but lighteval is moving towards using inspect-ai as well. I'm adding a few utilities for comparing and evaluating hf-inference-providers. For example I added :all to be able to compare all the providers in one line. If you think that's interesting might be worth mentioning at the end!

@pcuenca
Copy link
Member

pcuenca commented Nov 6, 2025

it's in scope of the blog but lighteval

I had the same thought, not sure if in scope either. Maybe worth adding just a sentence with a link, but your call (of course) @dvsrepo

@dvsrepo
Copy link
Contributor Author

dvsrepo commented Nov 6, 2025

great blog post ! Don't know if it's in scope of the blog but lighteval is moving towards using inspect-ai as well. I'm adding a few utilities for comparing and evaluating hf-inference-providers. For example I added :all to be able to compare all the providers in one line. If you think that's interesting might be worth mentioning at the end!

it's in scope of the blog but lighteval

I had the same thought, not sure if in scope either. Maybe worth adding just a sentence with a link, but your call (of course) @dvsrepo

@NathanHB, it would be awesome to add a reference/references to lighteval, even at each section (example) level. Would you be open to add some changes, or you prefer I add them?

@NathanHB
Copy link
Member

NathanHB commented Nov 6, 2025

Added a small line at the end, feel free to rephrase if needed :)

@dvsrepo
Copy link
Contributor Author

dvsrepo commented Nov 6, 2025

Added a small line at the end, feel free to rephrase if needed :)

Great @NathanHB ! I rephrased it a bit and moved it to the second bullet point, let me know if the working seems right to you

@dvsrepo
Copy link
Contributor Author

dvsrepo commented Nov 7, 2025

we're all set from my side, thanks a lot for the reviews @pcuenca @davanstrien @NathanHB !

Copy link
Contributor

@Vaibhavs10 Vaibhavs10 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice! Looks great! 🔥

@Vaibhavs10 Vaibhavs10 merged commit 8c0755c into huggingface:main Nov 12, 2025
1 check passed
@Vaibhavs10
Copy link
Contributor

Merged this - open PRs are detrimental to progress ^^ (we can iterate afterwards if needed)

@dvsrepo
Copy link
Contributor Author

dvsrepo commented Nov 12, 2025

Merged this - open PRs are detrimental to progress ^^ (we can iterate afterwards if needed)

Thanks for merging @Vaibhavs10 !

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.

6 participants