soda-inria/tabicl
TabICLv2: A state-of-the-art tabular foundation model
This tool helps scientists, marketers, traders, and other professionals quickly get accurate predictions from their business data, without needing to spend time fine-tuning complex models. You provide a dataset with rows of observations and columns of features (like a spreadsheet), and it outputs predictions or classifications for new, unseen data. It's designed for anyone who needs reliable results from tabular data for tasks like predicting sales, identifying customer segments, or forecasting market trends.
603 stars. Actively maintained with 10 commits in the last 30 days.
Use this if you need highly accurate predictions or classifications from tabular data without extensive model configuration or hyperparameter tuning.
Not ideal if your dataset is extremely small (fewer than 300 samples) or if you need to deeply understand and interpret the inner workings of the model's decision-making process.
Stars
603
Forks
80
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/soda-inria/tabicl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
PriorLabs/TabPFN
⚡ TabPFN: Foundation Model for Tabular Data ⚡
pyg-team/pytorch-frame
Tabular Deep Learning Library for PyTorch
NVIDIA-Merlin/NVTabular
NVTabular is a feature engineering and preprocessing library for tabular data designed to...
PriorLabs/tabpfn-extensions
Community extensions for TabPFN - the foundation model for tabular data. Built with TabPFN! 🤗
pytorch-tabular/pytorch_tabular
A unified framework for Deep Learning Models on tabular data