Worked on the dice-group/dice-embeddings repository to expand model support for knowledge graph embeddings by integrating the TransD, TransF, TransH, and TransR models into the PykeenKGE class. Used Python to update regularizer handling, ensuring stable training across the new models. Extended the test suite to include these models and implemented Mean Reciprocal Rank (MRR) thresholds, validating compatibility and preventing regressions. Focused on model integration and comprehensive testing, aligning with business goals for robust and scalable embeddings. No major bugs were reported during this period, and all changes were documented to support maintainability and future development within the codebase.