BlobNotFound: The specified blob does not exist.

[AnFreTh]

Hi, thanks for the great repo.
I am having a small issue getting the pretrained model to run. Using the example from the readme:

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.33, random_state=42
)

# MotherNetClassifier encapsulates a single instantiation of the model.
# This will automatically download a model from blob storage

classifier = MotherNetClassifier(device="cpu")

classifier.fit(X_train, y_train)
y_eval, p_eval = classifier.predict(X_test, return_winning_probability=True)

print("Accuracy", accuracy_score(y_test, y_eval))

# Ensembling as described in the TabPFN paper an be performed using the EnsembleMeta wrapper
ensemble_classifier = EnsembleMeta(classifier)

gives the following error

Downloading model from https://amuellermothernet.blob.core.windows.net/models/mn_Dclass_average_03_25_2024_17_14_32_epoch_3970.pickle 
HTTPError: HTTP Error 404: The specified blob does not exist.

[susie-ku]

Hello! I faced the same issue. Additionally, I am interested in regression checkpoint for MotherNet and GAMFormer

[amueller]

Sorry, just seeing this. There's no regression checkpoint for MotherNet, I can try to dig up a GAMFormer one, we haven't done a lot of work on that.
Does the error persist on the development branch?