ONNX exports of TabICLv2, KumoTabular (small, medium, large), KumoRelational, Chronos-2 and Kumo-Anomaly for Tabular Data Workbench
b043bdf verified | license: other | |
| license_name: bsd-3-clause-openmdw-1.1-apache-2.0 | |
| license_link: LICENSE.md | |
| library_name: onnx | |
| base_model: | |
| - jingang/TabICL | |
| - nvidia/Kumo-Tabular | |
| - nvidia/Kumo-Relational | |
| - amazon/chronos-2 | |
| - autogluon/chronos-2-small | |
| - nvidia/Kumo-Anomaly | |
| base_model_relation: quantized | |
| tags: | |
| - onnx | |
| - onnxruntime-web | |
| - webgpu | |
| - tabular-classification | |
| - tabular-regression | |
| - time-series-forecasting | |
| - anomaly-detection | |
| - tabular-foundation-model | |
| - relational-foundation-model | |
| - in-context-learning | |
| # ONNX models for Tabular Data Workbench | |
| Unofficial ONNX conversions of six open foundation models, made for Tabular | |
| Data Workbench, a browser app that runs them with onnxruntime-web on WebGPU | |
| or WebAssembly. The weights are the upstream authors': the `fp32` files hold | |
| them unchanged, and the `f16w` files store the larger ones as float16. The | |
| upstream authors have not reviewed or endorsed these conversions. | |
| | folder | models | upstream | licence | size (fp32 + f16w) | | |
| | --- | --- | --- | --- | --- | | |
| | [`tabicl/`](tabicl/README.md) | TabICLv2 classifier and regressor | [jingang/TabICL](https://huggingface.co/jingang/TabICL) (Soda team, Inria) | BSD-3-Clause | 339 MB | | |
| | [`kumo/`](kumo/README.md) | Kumo Tabular small, medium and large, classifier and regressor | [nvidia/Kumo-Tabular](https://huggingface.co/nvidia/Kumo-Tabular) (NVIDIA) | OpenMDW-1.1 | 1.2 GB (f16w only) | | |
| | [`rfm/`](rfm/README.md) | Kumo Relational classifier and regressor | [nvidia/Kumo-Relational](https://huggingface.co/nvidia/Kumo-Relational) (NVIDIA) | OpenMDW-1.1 | 367 MB | | |
| | [`tsfm/`](tsfm/README.md) | Chronos-2, Chronos-2 small, Kumo-Anomaly | [amazon/chronos-2](https://huggingface.co/amazon/chronos-2), [autogluon/chronos-2-small](https://huggingface.co/autogluon/chronos-2-small) (Amazon), [nvidia/Kumo-Anomaly](https://huggingface.co/nvidia/Kumo-Anomaly) (NVIDIA) | Apache-2.0 | 901 MB | | |
| Each folder holds a `manifest.json` (every file's size and sha256, the | |
| graphs' inputs and outputs, model settings and parity figures), the licence | |
| and notice files for its models, and each graph in two variants. `fp32` has | |
| the weights as released. `f16w` stores every float32 weight of 1,024 or more | |
| elements as float16 and casts it back to float32 on load, which halves the | |
| download and keeps compute in float32. `kumo/` has the `f16w` variant only. | |
| The README in each folder describes its graphs, how they were made and how | |
| closely they match the reference implementation. | |
| The graphs are the networks only. Preprocessing, ensembling, sampling and | |
| decoding stay outside them, as in the reference packages, and the app | |
| implements them in TypeScript. The `models/` folder of Tabular Data Workbench | |
| has the export scripts and the numpy references for these steps. | |
| ## Use in the app | |
| The app reads `<base>/<folder>/manifest.json` and the files it lists, and | |
| checks each file's sha256 before caching it. To serve the models from this | |
| repository, build the app with the base URL pinned to a commit: | |
| ```sh | |
| VITE_MODELS_BASE_URL=https://huggingface.co/ScriptSmith/tabular-data-workbench-onnx/resolve/<commit>/ pnpm build | |
| ``` | |
| ## How they were made | |
| The scripts are in the `models/` folder of Tabular Data Workbench, one uv | |
| workspace. They use PyTorch 2.14 on CPU and the `torch.onnx` dynamo exporter | |
| at opset 18 (opset 20 for `kumo/`), and check the graphs with onnxruntime | |
| 1.30: | |
| ```sh | |
| # from the root of the Tabular Data Workbench source | |
| (cd models/tabicl && uv run export.py) | |
| (cd models/kumo && uv run export.py) | |
| node models/rfm/dump_shop.mjs # once: the sample tables rfm's checks run on | |
| (cd models/rfm && uv run export.py) | |
| (cd models/tsfm && uv run export_chronos2.py && uv run export_kumo.py) | |
| ``` | |
| Every export checks its graphs against the reference package (tabicl, | |
| structured-data-models, chronos-forecasting) before it writes the manifest. | |
| The exports also remove the exporter's node metadata and doc strings, which | |
| hold stack traces with the paths of the machine that ran them. | |
| ## Licences | |
| The folders are under different licences, listed in [`LICENSE.md`](LICENSE.md): | |
| - `tabicl/`: BSD-3-Clause, Copyright (c) 2025, Soda team @ Inria (`tabicl/LICENSE`). | |
| - `kumo/`: OpenMDW-1.1, Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES | |
| (`kumo/LICENSE`), with a notice of origin and changes (`kumo/NOTICE`, which | |
| also carries the BSD-3-Clause notice for the TabICLv2-derived code) and the | |
| Apache-2.0 licence of structured-data-models (`kumo/LICENSE.structured-data-models`). | |
| - `rfm/`: OpenMDW-1.1, Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES | |
| (`rfm/LICENSE`), with NVIDIA's notice for the TabICLv2 weights it was | |
| fine-tuned from (`rfm/THIRD-PARTY-NOTICES.txt`, BSD-3-Clause) and the | |
| Apache-2.0 licence of structured-data-models (`rfm/LICENSE.structured-data-models`). | |
| - `tsfm/`: Apache-2.0 (`tsfm/LICENSE`), with Amazon's and NVIDIA's notices | |
| and a statement of the changes (`tsfm/NOTICE`), and DPM-Solver's MIT | |
| licence (`tsfm/THIRD-PARTY-NOTICES.txt`). | |
| Keep each folder's licence and notice files with its ONNX files when | |
| redistributing them. | |