Neuralk-AI 发布 Seldon 表格基础模型，0.2B 参数、开放权重

Like 1

Follow

Neuralk-AI 22

Tabular Classification

Safetensors

tabular

foundation-model

in-context-learning

synthetic-prior

License: neuralk-seldon-license

Model card Files Files and versions xet

Community

Copy to bucket

You agree to the terms of the Neuralk Seldon License.</p>\n","classNames":"hf-sanitized hf-sanitized-DLLIrN0q1H2TwOESr6ZEV"},"gated":"auto","profileSharing":{"username":true,"email":true},"isLoggedIn":false,"repoId":"Neuralk-AI/seldon","repoType":"model","isGoogleGemma":false,"requiresPaidPlan":false}"> You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

You agree to the terms of the Neuralk Seldon License.

Seldon TFM Family Model family

Quickstart

Benchmark

Architecture

Pretraining: a synthetic prior

Seldon TFM Family

Seldon is a tabular foundation model by Neuralk-AI. It predicts on new rows through in-context learning: you give it labeled example rows as context, and it predicts the target for new rows in a single forward pass, with no training or hyperparameter tuning on your data.

This repo contains seldon (213.5M parameters). For now, only the classification checkpoint is released.

Model family

Variant Parameters Availability

seldon-mini 27.4M Open weights

seldon 213.5M Open Weights

seldon API – Neuralk API

Quickstart

pip install neuralk-oss

from neuralk_oss import SeldonClassifier

clf = SeldonClassifier.from_pretrained("seldon", device="cuda") clf.fit(X_train, y_train) # stores the context; no gradient updates preds = clf.predict(X_test) proba = clf.predict_proba(X_test)

Benchmark

Head-to-head win rate on TabArena classification (38 datasets, 594 folds), each model with its default settings.

Architecture

Seldon follows the same design as Kumo Tabular and TabFM: the table is first compressed into one representation per row, and in-context learning then runs on these row representations.

Pretraining: a synthetic prior

Seldon is pretrained only on synthetically generated datasets drawn from a prior developed by Neuralk. No real-world data was used in pretraining. The prior is built on structural causal models (SCMs): each synthetic task comes from a randomly sampled causal graph whose nodes are linked by randomly drawn functional relationships and noise, and the features and target are read off this graph. The main goal of the prior is diversity. Its new, richer generative mechanisms go beyond classical SCM priors and vary:

As a result, the model sees a much wider range of tabular problems during pretraining than any collection of real datasets would provide, and learns a general way of doing in-context inference that carries over to real-world tables.

Safetensors

Model size

0.2B params

Tensor type

F32 ·

Files info