📊 Add SWE-bench evaluation results for princeton-nlp/SWE-bench_Verified
#1
by prithivMLmods - opened
No description provided.
dummy -- test_commit.
Closing this PR.
prithivMLmods changed pull request status to closed
Hey ! Just in case you haven't seen it we revamped how to add results to models, it uses a yaml file now 🤗
https://huggingface.co/docs/hub/en/eval-results#benchmark-datasets
Hi, @SaylorTwift thanks for the links!
I’ve read the docs, btw.
I just checked the formatter in Transformers inference, particularly the framework.
So I’ll be following the .yaml format in case I merge the evals.
Thank you!
Haha,
I’ve just completed an experimental template for fully eval a language model using Transformers.
And I just saw that you have a blog about it. - benchmarking-on-the-hub
Awesome!
ahah hope you will find it useful :)