How to choose a Sentence Transformer from Hugging Face

As a quick recap, Domain largely describes the high-level notion of what the dataset is about. In addition to Domain, there are many Tasks used to produce vector embeddings. Unlike language models, in which most models use the training task of "predict the masked out token", embedding models are trained in a much broader set of ways. For example, Duplicate Question Detection might perform better with a different model than one trained with Question Answering. It is a good rule of thumb to find models that have been trained within the same domain as your use case.