Nori-30M is the ~29.2M-parameter variant of Nori, a tabular foundation model for regression via in-context learning (ICL). Given a few labeled rows as context, it predicts on new query rows in a single forward pass, with no task-specific training or fine-tuning. The model is trained entirely on synthetic data. Mean and median R² across 96 regression tasks from three public benchmark suites, on the same protocol as the base Nori: Stronger than the ~6M base on every suite. Evaluated with the bundled default inference config and the large-GPU protocol (up to 50k context rows per dataset). Paste this into Claude Code, Cursor, or any AI coding assistant and it will wire python from synthefynori…
Nori-100M is the ~98.3M-parameter variant of Nori, a tabular foundation model for regression via in-context learning (ICL).
Parameters—
Context—
Weights395.2 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads10.3k
Model Card
By Synthefy, published under apache-2.0, revision 467ae9704fb0.
Nori-100M is the ~98.3M-parameter variant of Nori, a tabular foundation model for regression via in-context learning (ICL). Given a few labeled rows as context, it predicts on new query rows in a single forward pass, with no task-specific training or fine-tuning. The model is trained entirely on synthetic data. It uses a GPU when one is available and falls back to CPU. A one-shot helper skips the object predict follows the TabPFNRegressor.predict contract: pass outputtype="mean" (default), "median", or "mode" to choose the point estimate drawn from the model's predictive distribution. To run from a local checkpoint instead of the Hub, pass a path: NoriRegressor(modelpath="path/to/nori.pt").…
Read Synthefy's full model card
Nori-100M is the ~98.3M-parameter variant of Nori, a tabular foundation model for regression via in-context learning (ICL). Given a few labeled rows as context, it predicts on new query rows in a single forward pass, with no task-specific training or fine-tuning. The model is trained entirely on synthetic data.
- Documentation: https://docs.synthefy.com/nori/
- Repository: https://github.com/Synthefy/synthefy-nori
- Library:
pip install synthefy-nori - Checkpoint:
nori.pt(this repo) - Parameters: ~98.3M (98,304,698)
- Architecture: 42 layers, embed_dim 352, hid_dim 1056, 8 heads
- License: Apache-2.0
Usage
pip install synthefy-nori
from sklearn.datasets import load_diabetes
from sklearn.model_selection import train_test_split
from synthefy_nori import NoriRegressor
X, y = load_diabetes(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
model = NoriRegressor(model="nori-100m") # downloads these weights from the Hub on first use
model.fit(X_train, y_train) # "fit" just stores the labeled rows as context
pred = model.predict(X_test) # predictions in a single forward pass, no training
It uses a GPU when one is available and falls back to CPU. A one-shot helper skips the object entirely:
from synthefy_nori import predict
pred = predict(X_train, y_train, X_test, task="regression", model="nori-100m")
predict follows the TabPFNRegressor.predict contract: pass output_type="mean" (default),
"median", or "mode" to choose the point estimate drawn from the model's predictive
distribution.
To run from a local checkpoint instead of the Hub, pass a path:
NoriRegressor(model_path="path/to/nori.pt").
This model is public: the first call downloads and caches it automatically, with no token and no
access request. A Hugging Face token (read scope) is only worth setting if you hit anonymous
download rate limits — provide it via export HF_TOKEN=hf_..., hf auth login, or
NoriRegressor(model="nori-100m", token="hf_...").
Intended use & limitations
- Intended for small-to-medium tabular regression where in-context learning is attractive (no per-task training).
- Limitations: dense O(N²) sample attention bounds practical context size, so the current gap vs the best baselines is on large-N / long-context tables. Trained entirely on synthetic data; no benchmark data is used in training.
Citation
@software{synthefy_2026_20710462,
author = {Synthefy and
Li, Po-han and
Narayanan, Aditya and
Narasimhan, Sai Shankar and
Mallampalli, Raghav and
Agrawal, Aahan and
Ajan, Bekzat and
Shah, Raimi and
Agarwal, Shubhankar},
title = {Synthefy Nori: Tabular Foundation Model for Regression},
month = jun,
year = 2026,
publisher = {Zenodo},
version = {0.6.0},
doi = {10.5281/zenodo.20710462},
url = {https://doi.org/10.5281/zenodo.20710462},
}
License
Configuration
- Model type
- features-transformer
Identity and Version
- Repository
- Synthefy/Nori-100M
- Publisher
- Synthefy
- Task
- Tabular classification
- Modality
- Tabular
- Library
- synthefy-nori
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 467ae9704fb0ab328c0d2f850602c27123928b48
- First published
- 2026-08-18
- Last updated
- 2026-08-24
Files and Weights
5 files, 395.6 MB in total. The weights are 1 file totalling 395.2 MB in pt.
Weights1 file · 395.2 MB
Configuration1 file · 535 B
Documentation1 file · 3.8 KB
Other1 file · 398.4 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| nori.pt | Weights | 395.2 MB | 9528b87157da |
| config.json | Configuration | 535 B | — |
| README.md | Documentation | 3.8 KB | — |
| synthefy_nori_banner.png | Other | 398.4 KB | d82abad6f338 |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 395.2 MB
Download from Synthefy
Released by Synthefy through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 395.2 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Nori-100M
Can I use Nori-100M commercially?
Yes. Nori-100M is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Go to SAP-RPT Playground ↗ Note: This model and repository were formerly known as ConTextTab. While the code and repository have now been updated in line with the new name sap-rpt-1-oss, the model checkpoint and functionality remain identical. Implementation of the deep learning model with the inference pipeline described in the paper "ConTextTab: A Semantics-Aware Tabular In-Context Learner". Tabular in-context learning (ICL) has recently achieved state-of-the-art (SOTA) performance on several tabular prediction tasks. Previously restricted to classification problems on small tables, recent advances such as TabPFN and TabICL have extended its use to larger datasets. While being…
Nori is a tabular foundation model for regression via in-context learning (ICL). Given a few labeled rows as context, it predicts on new query rows in a single forward pass, with no task-specific training or fine-tuning. The model is trained entirely on synthetic data. Mean and median R² of the base model across 96 regression tasks from three public benchmark suites (single H200, up to 50K context rows per dataset): Large-N / long-context tables (common in TabArena) are the current focus of the large-table training stages. These numbers are reproducible end-to-end with one command — see Reproducing these numbers. Paste this into Claude Code, Cursor, or any AI coding assistant and it will…
EXAONE Tabular is a transformer-based foundation model for tabular data that solves classification and regression through in-context learning: you pass the labeled rows to fit and the model predicts new rows in a single forward pass — no gradient updates and no per-dataset training. This repository is the exaonetabular inference runtime — a self-contained package that loads a released checkpoint and serves predictions through a small, scikit-learn-style API. The code here is permissively licensed; the released weights are non-commercial — see Both checkpoints are released: EXAONETabularClassifier and EXAONETabularRegressor each fetch their own weights with a single frompretrained() call.…
TabPFN is a transformer-based foundation model for tabular data that leverages prior-data based learning to achieve strong performance on small tabular datasets without requiring task-specific training. For detailed usage examples and best practices, check out: - Python ≥ 3.9 - PyTorch ≥ 2.1 - scikit-learn ≥ 1.0 This repository hosts the production TabPFN-v2 base checkpoints. Files matching the pattern tabpfn-v2-classifier-finetuned-.ckpt are content-identical aliases of the corresponding base checkpoints (e.g. tabpfn-v2-classifier-finetuned-gn2p4bpt-xp6f0iqb.ckpt is identical to tabpfn-v2-classifier-gn2p4bpt.ckpt; tabpfn-v2-classifier-finetuned-zk73skhh.ckpt is identical to…
TabFM is a zero-shot tabular foundation model from Google Research. It supports classification and regression on structured/tabular data with mixed numerical and categorical columns, requiring no fine-tuning or hyperparameter search - training examples are passed as context and predictions are made in a single forward pass. This repository contains the PyTorch weights. For the JAX/Flax weights see You can also load directly using the HuggingFace Hub API: Developed by the Google Research team. - Tabular data with numerical and/or categorical columns - Binary and multiclass classification (up to 10 classes) TabFM uses alternating row and column attention to capture both feature interactions…