Samuel Müller
Samuel Müller
**Is your feature request related to a problem? Please describe.** So far you have integration for AutoAugment and RandAugment in the repo as well as some settings that seem to...
I got an error during `import hebo` with this specification, but not when I fix pymoo to 0.5.0 https://github.com/huawei-noah/HEBO/blob/405dc4ceb93a79f0d1f0eaa24f5458dd26de1d05/HEBO/requirements.txt#L4
I'd love to see an integration of HEBO as baseline right into this benchmark. It seems to be the strongest baseline right now. :)
Did you deprecate the vehicle enpoint? Will it come back? *I would love that!*
I don't really understand the visualizations tbh, so I wanted to turn them off, but viz=False, leads to the following error: ``` --------------------------------------------------------------------------- UnboundLocalError Traceback (most recent call last) [](https://ucrqhfq45wo-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab_20240403-060136_RC00_621473488#)...
Our test sets have duplicates, while we deduplicate them in our eval code, it would be better to just not have them in the first place s.t. we don't accidentally...
Hey there, Thanks a lot for this super nice LLM benchmark! Looking at the new release of Grok3 being clearly the top-1 model, I wondered whether you could make some...
I removed the option by having a conditional inside our botorch model, as I understand it to only impact this model and other models might use this keyword arg to...
### Describe your issue. We have a unit-test that is rather simple, which is passed easily with scipy