Spaces:
Running
Running
|
Download README.md from shreyask/kumo-tabular-web: direct link, hf CLI and curl.
- Browser
- Download file 1.07 kB
-
https://huggingface.co/spaces/shreyask/kumo-tabular-web/resolve/main/README.md
- Command line
-
hf download hf://spaces/shreyask/kumo-tabular-web/README.md
-
curl -L -o README.md https://huggingface.co/spaces/shreyask/kumo-tabular-web/resolve/main/README.md
1.07 kB
metadata
title: Kumo Tabular in the Browser
emoji: 📊
colorFrom: green
colorTo: gray
sdk: static
app_file: index.html
pinned: false
license: apache-2.0
short_description: Zero-shot tabular predictions on your CSV, fully in-browser
models:
- onnx-community/kumo-tabular-small-classifier-ONNX
- onnx-community/kumo-tabular-small-regressor-ONNX
- nvidia/Kumo-Tabular
tags:
- tabular
- webgpu
- duckdb
- transformers.js
Kumo Tabular in the Browser
Drop a CSV or Parquet file, pick a target column, and get zero-shot predictions from NVIDIA's Kumo Tabular (Small). DuckDB-WASM loads and queries the data; the model runs as ONNX on WebGPU (WASM fallback) through Transformers.js. Nothing leaves the page.
Models: classifier, regressor (OpenMDW-1.1). Code: shreyaskarnik/kumo-tabular-web (Apache-2.0).