RuntimeError: Fail to call predict with error: {'detail': 'Our prediction service is currently overloaded. Please try again later.'}

[zongyaowang-bjtu]

First of all, I would like to thank you for developing TABPFN-client—it's been incredibly helpful and efficient in my projects. However, in the past few days, I’ve been encountering an issue while using the TabPFNClassifier. I keep getting the following error when trying to make predictions:
RuntimeError: Fail to call predict with error: {'detail': 'Our prediction service is currently overloaded. Please try again later.'}
It seems that the prediction service is overloaded. Is there a workaround for this issue, or any steps I can take to resolve it? I'd appreciate any advice on how to move forward with this.
Thanks in advance for your help!

[liam-sbhoo]

Hi @zongyaowang-bjtu

Thank you for using our library, and we are sorry that you are facing this overloaded error.

Sometimes this happens when the job is taking too long. Or it could also be that we have too many requests at once. Perhaps you could try using less estimators (n_estimators in the config) or try again later.

We're working on optimizing things and getting more capacity to run this service smoother :)