alt.freeweights.text / kumo-tabular-small-regressor-ONNX

From:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.textSubject:

kumo-tabular-small-regressor-ONNX

Date: 2026-11-15Commit: 71ad7c7Signed: 2DC28CC7B26A283B ✓

Tabular regression model. Onnx weights, 120 MB in all. Published by onnx-community under OpenMDW-1.1.

text

120MBkumo-tabular-small-regressor-ONNXonnxcustom terms

FactsParamsnot statedSize120 MBFormatsonnxTasktabular regressionLicenseOpenMDW-1.1From sourcecustom termsread terms

# custom terms: read the license before you download
$ fw get onnx-community/kumo-tabular-small-regressor-ONNX
# manifest sha256 c55d7cb60db5… · 120 MB · 8 files
$ fw verify ./kumo-tabular-small-regressor-ONNX onnx-community/kumo-tabular-small-regressor-ONNX

From sourceHosted (signed)onnx-community/kumo-tabular-small-regressor-ONNXLast check: 2026-11-15 00:25 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run2 Convert3 Scan1

Runs with

Ranked by fit to this model (onnx), then by GitHub stars.

Ultralytics OpenVINO

Convert with

ONNX

Optimum

Olive

Scan with

ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 120 MB
Weights: 120 MB (ONNX)
Parameters: not stated
Formats: onnx
Task: tabular regression
License: OpenMDW-1.1 (custom)
Files: 8, each with a sha256
Publisher: onnx-community
Added: 2026-11-15
Section: alt.freeweights.text

Lineage

Original release from the publisher.

Base model: nvidia/Kumo-Tabular

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 00:25 UTC	passed

Model card

From the publisher at commit 71ad7c7. Shown as plain text with links; images open at the publisher.

Kumo Tabular Small, regressor (ONNX)#

ONNX conversion of the Small regressor of NVIDIA's Kumo Tabular (small/regressor.pt, revision v1.0.0), a tabular foundation model that predicts new rows from labeled context rows in one forward pass, with no training. For the model, its training and its limits see the original card, the blog post and structured-data-models.

Try it in your browser: Kumo Tabular in the Browser (drop a CSV or Parquet file; DuckDB-WASM + WebGPU; your data stays on the page). Code: shreyaskarnik/kumo-tabular-web.

Graph#

onnx/model.onnx + onnx/model.onnx_data, fp32, 120 MB. It is the inner model (_KumoTabular.forward) with dynamic rows, context rows and columns:

x [R, C] float32: context rows first, then query rows, already preprocessed
y_context [R_context] float32, standardized with the context mean and population std
categorical_mask [C] bool: which columns came from categorical features
logits [R_query, 999]: quantiles q001…q999 of the standardized target; sort, multiply by the context std and add the mean; the point estimate is their mean

The graph expects sdm's preprocessing (standardize, clip, sigma-clip, category codes and counts; see sdm/models/kumo/tabular/recipe.py). The browser demo ports it to TypeScript and checks it value by value against sdm. It loads with Transformers.js AutoModel (device: "webgpu") and runs on ONNX Runtime WebGPU, WASM or CPU.

Conversion and checks#

torch.onnx.export (dynamo, opset 20). One op needed a custom lowering: aten.remainder.Scalar with a symbolic divisor (index % num_columns in the column grouping) becomes ONNX Mod. Scripts are in conversion/.

ONNX Runtime (CPU) against PyTorch on inputs captured from real sdm runs: max |diff| 4.4e-5 (diabetes (442×10), California housing (1500×8); end to end in the browser within 6e-6 (relative) of sdm's point estimates).
WebGPU (Chrome, M3 Pro), same inputs: max |diff| ≤ 2e-4.

License#

The weights are NVIDIA's, under the OpenMDW-1.1 license (included); this is a format conversion with no change to them. Converted by @shreyask.

Files

8 files · 120 MBWeights 120 MB (ONNX). Sizes and sha256 from the signed manifest.

Hide all 8 files with their sha256

File	Size	sha256
.gitattributes	1.58 KB	b2edd226c6b1cd2d01eef5665bd45729424086f88ce4e410e183a8795b917f21
LICENSE	2.69 KB	44b43ed7b8e0f987dc5e90fb6cb4b901eccf0b14dc9f17a9033951603851d37d
README.md	2.79 KB	8a14c1fa8beb42a2a13f5612409eaf215efa189f72d203ee12aea1c796e0650b
config.json	440 B	1f22b731f03883fa1f8d41d4ac84678d49849bc874a083c073d2cbb82f7c484a
conversion/export_onnx.py	6.35 KB	7e1fc7a980c764855b55e8efb8388ac5eb627acd6a7ace42033dacab2b377f91
conversion/fixtures.py	6.67 KB	8956dd180c79e235608f4918f3cb9d4332c1e19455e37afb4d8c1510605fc2fb
onnx/model.onnx	6.02 MB	ec7b8a17758a124b99c41895245ad4f9d3208084e047e464cbbc5cd3e416305b
onnx/model.onnx_data	114 MB	13284564c5f94783eba45eb936909cc6e42b8f10d142292bea42e810ffb2acc7

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
71ad7c7f8a pinned now	2026-11-15 00:25 UTC	8 files · 120 MB

Use it

# custom terms: read the license before you download
$ fw get onnx-community/kumo-tabular-small-regressor-ONNX
# manifest sha256 c55d7cb60db5… · 120 MB · 8 files
$ fw verify ./kumo-tabular-small-regressor-ONNX onnx-community/kumo-tabular-small-regressor-ONNX

Terms that come with these files. OpenMDW 1.1: keep the agreement and the copyright notices with the files when you pass them on.

Custom license (custom). Read the license text first. Open this panel to show the commands once you accept its terms.

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/kumo-tabular-small-regressor-ONNX.json --dir ./kumo-tabular-small-regressor-ONNX
$ python3 fw.py verify ./kumo-tabular-small-regressor-ONNX ./onnx-community__kumo-tabular-small-regressor-ONNX.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/kumo-tabular-small-regressor-ONNX --revision 71ad7c7f8aa4325b1925ea2866820c4d8b5ac235 --local-dir ./kumo-tabular-small-regressor-ONNX

Run at home

License

Name: OpenMDW-1.1
Id: OpenMDW-1.1
Class: Custom terms
Redistribution: click-through
Listing: Hosted (signed)
Terms: OpenMDW 1.1: keep the agreement and the copyright notices with the files when you pass them on.
Decided: License as declared by the publisher. No person read it. 2026-11-15
Text in: LICENSE
Text sha256: 44b43ed7b8e0f987dc5e90fb6cb4b901eccf0b14dc9f17a9033951603851d37d
Terms gate: Yes. The commands stay folded until you open them after reading the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.textSubject: kumo-tabular-small-regressor-ONNXDate: 2026-11-15Commit: 71ad7c7Signed: 2DC28CC7B26A283B ✓

Upstream: onnx-community/kumo-tabular-small-regressor-ONNX
Pinned commit: 71ad7c7f8aa4325b1925ea2866820c4d8b5ac235
Manifest: kumo-tabular-small-regressor-ONNX.json · .minisig
Manifest sha256: c55d7cb60db53ddf9c8a26b8702effbd8b75d43f830da55ed287fed3127639c6
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 00:25 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/kumo-tabular-small-regressor-ONNX.json
$ curl -O https://freeweights.allternit.com/manifests/onnx-community/kumo-tabular-small-regressor-ONNX.json.minisig
$ minisign -Vm kumo-tabular-small-regressor-ONNX.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

nvidia/Kumo-Tabular (not in this catalog) · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it

Read license, then download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/kumo-tabular-small-regressor-ONNX

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. kumo-tabular-small-regressor-ONNX.json. Provenance. Takedown history: none.

Source

huggingface.co/onnx-community/kumo-tabular-small-regressor-ONNX

Related models

All of alt.freeweights.text →

From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B