# Contextual Learning

TabPFNMix is a tabular foundation model pretrained on purely synthetic datasets, utilizing an encoder-decoder Transformer architecture, suitable for tabular data regression tasks.

A foundational model for tabular data, pretrained on synthetic datasets generated by mixing random classifiers

CuBERT is a context-aware embedding model for Python source code, pre-trained based on the BERT architecture, designed for code understanding and analysis tasks.