RELEASE · MODELS · #1203
NVIDIA releases Kumo Tabular, an open foundation model for tabular prediction
NVIDIA released Kumo Tabular, an open-source foundation model for tabular classification and regression available on Hugging Face and GitHub under the OpenMDW-1.1 license. The Transformer-based model family (28M–215M parameters), pretrained on synthetic tables, predicts labels in a single forward pass with no task-specific training and tops benchmarks TabArena, BeyondArena, TALENT and ScoringBench.
KEY POINTS
- NVIDIA released Kumo Tabular, an open-source foundation model for tabular classification and regression available on Hugging Face and GitHub under the OpenMDW-1.1 license.
- The Transformer-based model family (28M–215M parameters), pretrained on synthetic tables, predicts labels in a single forward pass with no task-specific training and tops benchmarks TabArena, BeyondArena, TALENT and ScoringBench.
- Kumo Tabular applies in-context learning to enterprise tabular data, potentially reducing the need for task-specific feature engineering, training and deployment overhead for common business ML tasks.
WHY IT MATTERS
Kumo Tabular applies in-context learning to enterprise tabular data, potentially reducing the need for task-specific feature engineering, training and deployment overhead for common business ML tasks.