Kumo Tabular

Kumo Tabular

Open foundation model for tabular prediction

2 followers

NVIDIA Kumo Tabular is an open foundation model for tabular classification and regression, released by NVIDIA on Hugging Face. Given a labeled table, it predicts new rows in a single forward pass, no training, tuning or feature engineering. Comes in three sizes, 28M to 215M parameters, pretrained only on artificial data. Ranks first on four benchmarks: TabArena, BeyondArena, TALENT and ScoringBench.
Kumo Tabular gallery image
Kumo Tabular gallery image
Kumo Tabular gallery image
Kumo Tabular gallery image
Launch Team
Render Sandboxes: a computer for every agent
Render Sandboxes: a computer for every agentIsolated compute, persistent state and a real filesystem
Promoted