alt.freeweights.text / kumo-tabular-small-classifier-ONNX
From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.textSubject:

kumo-tabular-small-classifier-ONNX

Date: 2026-11-15Commit: db7fec7Signed: 2DC28CC7B26A283B ✓

Tabular classification model. Onnx weights, 116 MB in all. Published by onnx-community under OpenMDW-1.1.

text116MBkumo-tabular-small-classifier-ONNXonnxcustom terms
FactsParamsnot statedSize116 MBFormatsonnxTasktabular classificationLicenseOpenMDW-1.1From sourcecustom termsread terms
# custom terms: read the license before you download
$ fw get onnx-community/kumo-tabular-small-classifier-ONNX
# manifest sha256 7bc4134c6fed… · 116 MB · 8 files
$ fw verify ./kumo-tabular-small-classifier-ONNX onnx-community/kumo-tabular-small-classifier-ONNX
From sourceHosted (signed)onnx-community/kumo-tabular-small-classifier-ONNXLast check: 2026-11-15 00:25 UTC

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

Works with

Runs with

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

Convert with

Scan with

Overview

Size
116 MB
Weights
116 MB (ONNX)
Parameters
not stated
Formats
onnx
Task
tabular classification
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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 00:25 UTCpassed

Model card

From the publisher at commit db7fec7. Shown as plain text with links; images open at the publisher.

Kumo Tabular Small, classifier (ONNX)#

ONNX conversion of the Small classifier of NVIDIA's Kumo Tabular (small/classifier.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, 116 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] int32 class codes (0..K-1, K ≤ 10)
  • categorical_mask [C] bool: which columns came from categorical features
  • logits [R_query, 10]: slice to the number of classes, softmax

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| 1.25e-4 (breast cancer (569×30), iris, wine; end to end in the browser within 6e-6 of sdm's probabilities, no top class changed).
  • 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 · 116 MBWeights 116 MB (ONNX). Sizes and sha256 from the signed manifest.
Hide all 8 files with their sha256
FileSizesha256
.gitattributes1.58 KBb2edd226c6b1cd2d01eef5665bd45729424086f88ce4e410e183a8795b917f21
LICENSE2.69 KB44b43ed7b8e0f987dc5e90fb6cb4b901eccf0b14dc9f17a9033951603851d37d
README.md2.67 KB0a6b02cc3e6deceaf0b19c0bc04d3eb96312e11ba499a39b3860b0ea4e2a4f63
config.json453 B8c346843ae0ccd8c1b3881c1ca38b31ab2c46689727837aa1a5104fd7bfc5b8f
conversion/export_onnx.py6.35 KB7e1fc7a980c764855b55e8efb8388ac5eb627acd6a7ace42033dacab2b377f91
conversion/fixtures.py6.67 KB8956dd180c79e235608f4918f3cb9d4332c1e19455e37afb4d8c1510605fc2fb
onnx/model.onnx6.02 MBff4565a79dd2121599e01ac7c558a5221fad456c923df735f83b1463d352d9a7
onnx/model.onnx_data110 MB05c3e8b8f1fb5332272c3d752611a7c539873da6208bf249a0ea0b1e440c7d56
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
db7fec7ac0 pinned now2026-11-15 00:25 UTC8 files · 116 MB

Use it

# custom terms: read the license before you download
$ fw get onnx-community/kumo-tabular-small-classifier-ONNX
# manifest sha256 7bc4134c6fed… · 116 MB · 8 files
$ fw verify ./kumo-tabular-small-classifier-ONNX onnx-community/kumo-tabular-small-classifier-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-classifier-ONNX.json --dir ./kumo-tabular-small-classifier-ONNX $ python3 fw.py verify ./kumo-tabular-small-classifier-ONNX ./onnx-community__kumo-tabular-small-classifier-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-classifier-ONNX --revision db7fec7ac021759105caaaccc7865e329c1520a0 --local-dir ./kumo-tabular-small-classifier-ONNX

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-classifier-ONNXDate: 2026-11-15Commit: db7fec7Signed: 2DC28CC7B26A283B ✓
Upstream
onnx-community/kumo-tabular-small-classifier-ONNX
Pinned commit
db7fec7ac021759105caaaccc7865e329c1520a0
Manifest
kumo-tabular-small-classifier-ONNX.json · .minisig
Manifest sha256
7bc4134c6feda9579ae2c158bae80eb8b8e744cd140c2e1245b257350e4064fc
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-classifier-ONNX.json $ curl -O https://freeweights.allternit.com/manifests/onnx-community/kumo-tabular-small-classifier-ONNX.json.minisig $ minisign -Vm kumo-tabular-small-classifier-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-classifier-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-classifier-ONNX.json. Provenance. Takedown history: none.
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