merlin.models.tf.split_embeddings_on_size

merlin.models.tf.split_embeddings_on_size(embeddings: merlin.models.tf.core.combinators.ParallelBlock, threshold: int) → Tuple[List[merlin.models.tf.core.base.Block], List[merlin.models.tf.core.base.Block]]

split embedding tables in ParallelBlock based on size threshold (first dimension of embedding tables), return a tuple of two lists, which contain large embeddings and small embeddings