yandex-research/tabpfn-finetuning

On Finetuning Tabular Foundation Models Paper Code

19
/ 100
Experimental

This tool helps data scientists and machine learning engineers improve the accuracy of predictions on tabular datasets. You provide your existing tabular data, and it fine-tunes a powerful pre-trained model (TabPFNv2) to better fit your specific data, resulting in more accurate classification or regression outcomes.

No commits in the last 6 months.

Use this if you are working with small to medium-sized tabular datasets and want to achieve state-of-the-art prediction accuracy by adapting a foundation model to your specific data.

Not ideal if your datasets exhibit significant gradual temporal shifts or have extremely rich feature sets, as traditional methods might still perform better in those specific scenarios.

data-science machine-learning-engineering predictive-modeling tabular-data-analysis model-optimization
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 3 / 25

How are scores calculated?

Stars

35

Forks

1

Language

Python

License

Last pushed

Sep 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yandex-research/tabpfn-finetuning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.