| license: openmdw-1.1 | |
| base_model: | |
| - jingang/TabICL | |
| tags: | |
| - relational-foundation-model | |
| - structured-data-models | |
| # Kumo Relational | |
| Kumo Relational is NVIDIA's pretrained foundation model for classification and regression across related tables using in-context learning. It is based on KumoRFM-2 and combines row embeddings with relational message passing. | |
| ## Getting Started | |
| Install [`structured-data-models`](https://github.com/NVIDIA/structured-data-models) for inference: | |
| ```bash | |
| pip install git+https://github.com/NVIDIA/structured-data-models.git | |
| ``` | |
| Load the pretrained model and predict class probabilities: | |
| ```python | |
| import sdm | |
| model = sdm.models.KumoRelational(task="classification", device="cuda") | |
| probs = model( | |
| x_context=x_context, | |
| y_context=y_context, | |
| x_query=x_query, | |
| related_context_tables=related_context, | |
| related_query_tables=related_query, | |
| num_estimators=8, | |
| ) | |
| ``` | |
| To learn more, visit [structured-data-models](https://github.com/NVIDIA/structured-data-models). | |
| ## License and Third-Party Notice | |
| Kumo Relational weights are released under OpenMDW 1.1. | |
| Kumo Relational finetunes pretrained TabICLv2 weights, licensed under BSD-3-Clause. The upstream attribution, copyright notice, and complete BSD 3-Clause license text are preserved in `THIRD-PARTY-NOTICES.txt`. | |