# Tabular Classification Models: Open-Weight AI Source: https://savrn.com/models/tasks/tabular-classification Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by Task # Tabular Classification Models 45 open-weight tabular classification models in the SAVRN Model Hub, with Prior Labs, Autogluon and Synthefy publishing the most. 45Models 33Publishers 78K to 412MParameter range 8Licenses ## SAVRN's Take Nearly everything under tabular classification on our hub works the same way: hand the model labeled rows as context and it predicts new rows in a single forward pass, with no per-dataset training. Mitra and Nori are trained entirely on synthetic data. Thirty-six models carry the tag. Prior Labs publishes five, Autogluon four, Synthefy three, Google and the Stanford Tabular and Relational (STAR) Project two apiece. Hardware is not the decision here. Of the 11 entries that state a parameter count, FoMo-0D is the smallest at 5M and fela-tab the largest at 412M, and even fela-tab needs 1.0 GB at 16-bit. Autogluon's mitra-classifier, the most downloaded at 283,443 a month and the only one of the 36 we index with a live price, fits in 0.2 GB at 16-bit. The cheapest Index host for any of them is one MI300X at $1.85 an hour, which mostly sits idle at these sizes. Licensing is where we would spend review time. Twelve of the 36 are Apache 2.0, including mitra-classifier, Synthefy's Nori-30M at 199,373 downloads and SAP's sap-rpt-1-oss at 123,801, though SAP's is gated. Six are MIT. Eight are filed as other, and that bucket holds LG AI Research's EXAONE-Tabular at 72,651 and Prior Labs' TabPFN-v2-clf at 40,747, so read those terms first. Five state no license and two are CC BY-NC-SA 4.0, noncommercial by name. Synthefy describes both Nori entries as regression models, so match the task to your problem, not the tag. Then check the runtime: tabpfn, synthefy-nori and sap-rpt-1-oss each ship as their own package, which your team will maintain. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [mitra-classifier](https://savrn.com/models/mitra-classifier) | Autogluon | 76M | apache-2.0 | 283.4k | 1x MI300X, $1.85/hr | | [Nori-30M](https://savrn.com/models/nori-30m) | Synthefy | — | apache-2.0 | 199.4k | — | | [sap-rpt-1-oss](https://savrn.com/models/sap-rpt-1-oss) | SAP | — | apache-2.0 | 123.8k | — | | [Nori](https://savrn.com/models/nori) | Synthefy | — | apache-2.0 | 94.2k | — | | [EXAONE-Tabular](https://savrn.com/models/exaone-tabular) | LG AI Research | — | other | 72.7k | — | | [TabSTAR](https://savrn.com/models/tabstar) | Alan Arazi | 47M | cc-by-4.0 | 62.7k | 1x MI300X, $1.85/hr | | [TabPFN-v2-clf](https://savrn.com/models/tabpfn-v2-clf) | Prior Labs | — | other | 40.7k | — | | [mitra-classifier-2](https://savrn.com/models/mitra-classifier-2) | Autogluon | 76M | apache-2.0 | 37.2k | 1x MI300X, $1.85/hr | | [tabfm-1.0.0-pytorch](https://savrn.com/models/tabfm-1-0-0-pytorch) | Google | — | other | 32k | — | | [tabpfn_3](https://savrn.com/models/tabpfn-3) | Prior Labs | — | other | 24.6k | — | ## Licenses | License | Models | Commercial use | | --- | --- | --- | | [apache-2.0](https://savrn.com/models/licenses/apache-2-0) | 13 | Yes | | [mit](https://savrn.com/models/licenses/mit) | 12 | Yes | | other | 8 | Read the license | | not stated | 6 | Not stated | | [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) | 2 | Not without separate permission | | [gpl-3.0](https://savrn.com/models/licenses/gpl-3-0) | 1 | Read the license | | [cc0-1.0](https://savrn.com/models/licenses/cc0-1-0) | 1 | Read the license | | [cc-by-nc-nd-4.0](https://savrn.com/models/licenses/cc-by-nc-nd-4-0) | 1 | Read the license | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Prior Labs](https://savrn.com/model-publishers/prior-labs) | 5 | | [Autogluon](https://savrn.com/model-publishers/autogluon) | 4 | | [Synthefy](https://savrn.com/model-publishers/synthefy) | 3 | | [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) | 2 | | [(Ministry of) Silly Kicks](https://savrn.com/model-publishers/silly-kicks) | 2 | | [Google](https://savrn.com/model-publishers/google) | 2 | ## All 45 Models Model · Tabular classification ### [mitra-classifier](https://savrn.com/models/mitra-classifier) [Autogluon](https://savrn.com/model-publishers/autogluon) Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers. Mitra is based on a 12-layer Transformer of 72 M parameters, pre-trained by incorporating an in-context learning paradigm. To use Mitra classifier, install AutoGluon by running: A minimal example showing how to perform inference using the Mitra classifier: A minimal example showing how to perform fine-tuning using the Mitra classifier: This project is licensed under the Apache-2.0 License. Amazon Science blog: Mitra: Mixed synthetic priors for enhancing tabular foundation models Open weights apache-2.0 76M parameters [View model](https://savrn.com/models/mitra-classifier) Model · Tabular classification ### [sap-rpt-1-oss](https://savrn.com/models/sap-rpt-1-oss) [SAP](https://savrn.com/model-publishers/sap) 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… Access requested at publisher apache-2.0 sap-rpt-1-oss [View model](https://savrn.com/models/sap-rpt-1-oss) Model · Tabular classification ### [TabSTAR](https://savrn.com/models/tabstar) [Alan Arazi](https://savrn.com/model-publishers/alana89) To fit a pretrained TabSTAR model to your own dataset, install the package: Paper: TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations Open weights cc-by-4.0 47M parameters [View model](https://savrn.com/models/tabstar) Model · Tabular classification ### [mitra-classifier-2](https://savrn.com/models/mitra-classifier-2) [Autogluon](https://savrn.com/model-publishers/autogluon) Mitra-v2 classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers, including the new Hybrid SCM prior. It is the second generation of the Mitra classifier (autogluon/mitra-classifier), pre-trained with a 10x longer context, three times as many features, and an improved optimizer. On the TabArena and TALENT benchmarks it delivers state-of-the-art accuracy at the level of TabFM and EXAONE Tabular, while surpassing TabPFN-3 by a wide margin. The regression model is at autogluon/mitra-regressor-2, and the inference and fine-tuning code with our evaluation results is at autogluon/mitra-finetune. Mitra-v2 is based on a… Open weights apache-2.0 76M parameters [View model](https://savrn.com/models/mitra-classifier-2) Model · Tabular classification ### [tabpfn-mix-1.0-classifier](https://savrn.com/models/tabpfn-mix-1-0-classifier) [Autogluon](https://savrn.com/model-publishers/autogluon) TabPFNMix classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers. TabPFNMix is based on a 12-layer encoder-decoder Transformer of 37 M parameters. We use a pre-training strategy incorporating in-context learning, similar to that used by TabPFN and TabForestPFN. To use TabPFNMix classifier, install AutoGluon by running: A minimal example showing how to perform fine-tuning and inference using the TabPFNMix classifier: If you find TabPFNMix useful for your research, please consider citing the associated papers: This project is licensed under the Apache-2.0 License. Open weights apache-2.0 39M parameters [View model](https://savrn.com/models/tabpfn-mix-1-0-classifier) Model · Tabular classification ### [FoMo-0D](https://savrn.com/models/fomo-0d) [YuchenShen](https://savrn.com/model-publishers/yuchenshen) This model has been pushed to the Hub using the PytorchModelHubMixin integration Open weights mit 5M parameters [View model](https://savrn.com/models/fomo-0d) Model · Tabular classification ### [MetaTree](https://savrn.com/models/metatree) [Yufan Zhuang](https://savrn.com/model-publishers/yzhuang) Model is avaliable at https://huggingface.co/yzhuang/MetaTree 1. Install metatreelib: 2. Use MetaTree on your datasets to generate a decision tree model We show a complete example of using MetaTree at notebook If you have any questions related to the code or the paper, feel free to reach out to us at y5zhuang@ucsd.edu. If you find our paper and code useful, please cite us Open weights mit 151M parameters 256 tokens transformers [View model](https://savrn.com/models/metatree) Model · Tabular classification ### [mitra-classifier-1.1](https://savrn.com/models/mitra-classifier-1-1) [Autogluon](https://savrn.com/model-publishers/autogluon) Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers. Mitra is based on a 12-layer Transformer of 72 M parameters, pre-trained by incorporating an in-context learning paradigm. To use Mitra classifier, install AutoGluon by running: A minimal example showing how to perform inference using the Mitra classifier: A minimal example showing how to perform fine-tuning using the Mitra classifier: This project is licensed under the Apache-2.0 License. Amazon Science blog: Mitra: Mixed synthetic priors for enhancing tabular foundation models Open weights apache-2.0 76M parameters [View model](https://savrn.com/models/mitra-classifier-1-1) Model · Tabular classification ### [rt-plurel](https://savrn.com/models/rt-plurel) [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) RT-PluRel is a Relational Transformer checkpoint pair for in-context / few-shot entity prediction over multi-table relational databases (no per-task gradient training). Same architecture and file layout as stanford-star/rt-j — drop-in replacement. Architecture: ~85.6M blocks, dmodel 512, 8 heads, dff 2048 · text columns embedded with all-MiniLM-L12-v2 (dtext 384). Each folder contains model.safetensors (weights) and config.json (dims + text-embedding model). The paper/ subdirectory preserves the earlier RT-PluRel release:.pt checkpoints (12 blocks, dmodel 256, dff 1024) pretrained on synthetic relational databases generated by PluRel, plus the continued-pretraining and fine-tuned RelBench… Open weights cc-by-nc-sa-4.0 86M parameters pytorch [View model](https://savrn.com/models/rt-plurel) Model · Tabular classification ### [DigitalEduTransformers](https://savrn.com/models/digitaledutransformers) [SnowFlash383935](https://savrn.com/model-publishers/snowflash383935) Модель для соревнования DigitalEdu с использованием трансформеров. 9 эпох. Пример вывода: [False, True] Open weights gpl-3.0 101M parameters transformers [View model](https://savrn.com/models/digitaledutransformers) Model · Tabular classification ### [stonkfun-graduation-predictor](https://savrn.com/models/stonkfun-graduation-predictor) [Joshua Rhode](https://savrn.com/model-publishers/jrhode666) Tabular Transformer trained on 177,110 Stonkfun launches (status='graduated' label, 2.7% positive, time-ordered split). Leak-free features only: create-time metadata (name/symbol length, fees, creator, hour/dow, website) + 5m early-window candle features, computed by stonkfunfeatures.py, the same code the live scorer uses. - 123,976 train / 26,567 val / 26,567 test (time-ordered) Open weights mit 77,890 parameters transformers [View model](https://savrn.com/models/stonkfun-graduation-predictor) Model · Tabular classification ### [fela-tab](https://savrn.com/models/fela-tab) [Lowdown Labs](https://savrn.com/model-publishers/lowdown-labs) This model is a research preview. It is offered for advancing public science and for evaluation. It is not a substitute for a domain expert, and it is not a certified decision system. FelaTab reads a small table you already have and predicts the missing cells. You give it some example rows with their answers (the support rows) and one or more rows you want filled in (the query rows); it learns the pattern from your examples in a single pass and returns the answer with a calibrated confidence range. There is no per table training, no fitting, and no setup: you point it at a table and it predicts. It runs on a plain CPU with no GPU. It is a prior fitted network (a "foundation model for… Open weights apache-2.0 412M parameters transformers [View model](https://savrn.com/models/fela-tab) Model · Tabular classification ### [Nori-30M](https://savrn.com/models/nori-30m) [Synthefy](https://savrn.com/model-publishers/synthefy) 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… Open weights apache-2.0 synthefy-nori [View model](https://savrn.com/models/nori-30m) Model · Tabular classification ### [Nori](https://savrn.com/models/nori) [Synthefy](https://savrn.com/model-publishers/synthefy) 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… Open weights apache-2.0 synthefy-nori [View model](https://savrn.com/models/nori) Model · Tabular classification ### [EXAONE-Tabular](https://savrn.com/models/exaone-tabular) [LG AI Research](https://savrn.com/model-publishers/lg-ai-research) 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.… Open weights other [View model](https://savrn.com/models/exaone-tabular) Model · Tabular classification ### [TabPFN-v2-clf](https://savrn.com/models/tabpfn-v2-clf) [Prior Labs](https://savrn.com/model-publishers/prior-labs) 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… Open weights other tabpfn [View model](https://savrn.com/models/tabpfn-v2-clf) Model · Tabular classification ### [tabfm-1.0.0-pytorch](https://savrn.com/models/tabfm-1-0-0-pytorch) [Google](https://savrn.com/model-publishers/google) 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… Open weights other tabfm [View model](https://savrn.com/models/tabfm-1-0-0-pytorch) Model · Tabular classification ### [tabpfn_3](https://savrn.com/models/tabpfn-3) [Prior Labs](https://savrn.com/model-publishers/prior-labs) TabPFN-3 is a transformer-based foundation model that uses in-context-learning to solve tabular prediction problems in a forward pass. Inference code can be found at https://github.com/PriorLabs/TabPFN. More details can be found in the Model Report. Fitting a classifier and predicting looks like this: For more examples (e.g. how to train a regressor), see the github repo: https://github.com/PriorLabs/tabPFN! TabPFN-3 ships with default classification and regression checkpoints, plus a few experimental specialized variants. We recommend starting with the defaults — the variants can be useful in ensembling or HPO setups, or tried manually in the regime they were trained for. Their name… Open weights other [View model](https://savrn.com/models/tabpfn-3) Model · Tabular classification ### [tabpfn_2_5](https://savrn.com/models/tabpfn-2-5) [Prior Labs](https://savrn.com/model-publishers/prior-labs) TabPFN-2.5 is a transformer-based foundation model that uses in-context-learning to solve tabular prediction problems in a forward pass. Inference code can be found at https://github.com/PriorLabs/tabPFN. Fitting a classifier and predicting looks like this: For more examples (e.g. how to train a regressor), see the github repo: https://github.com/PriorLabs/tabPFN! Developed by Prior Labs. Regression and classification tasks with ≤50 000 samples and ≤2000 features in structured tabular format. - Not suitable for unstructured data (text, images); use API version for textual features. - Not tested for >50 000 samples or > 2000 features. Transformer with TabPFNv2-like alternating attention with… Open weights other [View model](https://savrn.com/models/tabpfn-2-5) Model · Tabular classification ### [Nori-100M](https://savrn.com/models/nori-100m) [Synthefy](https://savrn.com/model-publishers/synthefy) 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").… Open weights apache-2.0 synthefy-nori [View model](https://savrn.com/models/nori-100m) Model · Tabular classification ### [genomics-tf-prediction](https://savrn.com/models/genomics-tf-prediction) [Généreux Akotenou](https://savrn.com/model-publishers/genereux-akotenou) accuracy pipelinetag: tabular-classification - biology Open weights keras [View model](https://savrn.com/models/genomics-tf-prediction) Model · Tabular classification ### [tabpfn_3_5](https://savrn.com/models/tabpfn-3-5) [Prior Labs](https://savrn.com/model-publishers/prior-labs) TabPFN-3.5 is a transformer-based foundation model that uses in-context learning to solve tabular prediction problems in a forward pass. One checkpoint serves both classification and regression. Inference code can be found at https://github.com/PriorLabs/TabPFN. Fitting a classifier and predicting looks like this: TabPFNRegressor works the same way, off the same checkpoint. For more examples, see the github repo: https://github.com/PriorLabs/TabPFN. To use a specific checkpoint, pass its filename via modelpath: Every checkpoint ships with basic text and datetime column handling enabled (TRANSFORMTEXT, TRANSFORMDATES) and a feature limit of 20,000. Developed by Prior Labs. Regression and… Open weights other [View model](https://savrn.com/models/tabpfn-3-5) Model · Tabular classification ### [tabpfn_2_6](https://savrn.com/models/tabpfn-2-6) [Prior Labs](https://savrn.com/model-publishers/prior-labs) TabPFN-2.6 is a transformer-based foundation model that uses in-context-learning to solve tabular prediction problems in a forward pass. Inference code can be found at https://github.com/PriorLabs/tabPFN. Fitting a classifier and predicting looks like this: For more examples (e.g. how to train a regressor), see the github repo: https://github.com/PriorLabs/tabPFN! Developed by Prior Labs. Regression and classification tasks with ≤50 000 samples and ≤2000 features in structured tabular format. - Not suitable for unstructured data (text, images); use API version for textual features. - Not tested for >50 000 samples or > 2000 features. Transformer with TabPFNv2-like alternating attention with… Open weights other [View model](https://savrn.com/models/tabpfn-2-6) Model · Tabular classification ### [tabfm-1.0.0-jax](https://savrn.com/models/tabfm-1-0-0-jax) [Google](https://savrn.com/model-publishers/google) 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 JAX/Flax weights stored as Orbax checkpoints. For the PyTorch 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) - GPU/TPU acceleration via JAX (use bfloat16 dtype for… Open weights other tabfm [View model](https://savrn.com/models/tabfm-1-0-0-jax) Model · Tabular classification ### [DataScientst-models](https://savrn.com/models/datascientst-models) [ALİ OKTAY BBUS](https://savrn.com/model-publishers/oktaybbs) Trained models from a comprehensive ML/AI portfolio spanning 10 categories. All models were trained on real Kaggle datasets. Open weights mit keras [View model](https://savrn.com/models/datascientst-models) Model · Tabular classification ### [cernpeerenv-zmumu-dqn](https://savrn.com/models/cernpeerenv-zmumu-dqn) [D](https://savrn.com/model-publishers/dhdrl) Task. Binary classification of simulated dimuon events: does this event contain an opposite-sign muon pair whose invariant mass falls in (80, 100) GeV? Method. The classifier is trained with Stable-Baselines3 DQN or PPO inside a one-step Gymnasium wrapper. Each reset / step is one labeled event and then terminated=True. There is no horizon, no delayed credit assignment, and no control of a detector. Label. Computed from the same padded muon kinematics the policy sees: at least two muons, opposite charge, invariant mass in (massmin, massmax) with defaults 80–100 GeV. This is not generator-level Z truth and not a CMS official tag. Data for the reported numbers. Pythia8 Monte Carlo only… Open weights apache-2.0 stable-baselines3 [View model](https://savrn.com/models/cernpeerenv-zmumu-dqn) Model · Tabular classification ### [wine-quality](https://savrn.com/models/wine-quality) [Julien Chaumond](https://savrn.com/model-publishers/julien-c) No red wine was drunk (unfortunately) while training this model Open weights sklearn [View model](https://savrn.com/models/wine-quality) Model · Tabular classification ### [rt-j](https://savrn.com/models/rt-j) [Stanford Tabular and Relational (STAR) Project](https://savrn.com/model-publishers/stanford-star) Open weights cc-by-nc-sa-4.0 86M parameters [View model](https://savrn.com/models/rt-j) Model · Tabular classification ### [mbta-track-predictor](https://savrn.com/models/mbta-track-predictor) [Ryan Wallace](https://savrn.com/model-publishers/cubis) Predicts which MBTA commuter rail track/platform a train will use, using a small tabular neural-network ensemble trained on historical assignments. This card documents the artifacts in output/ensemble20250906124755. - trackpredictionensemblemodel0final.keras … trackpredictionensemblemodel5final.keras — individual ensemble members - trackpredictionensemblemodelbest.keras — best checkpoints during training (may match final) - trainingreport.md — training configuration and metrics Note: Ensemble training currently does not emit a vocab.json. See “Preprocessing & Vocab” below. Models expect integer indices for stationid and routeid, and raw directionid 0/1. In training, indices are produced by… Open weights apache-2.0 keras [View model](https://savrn.com/models/mbta-track-predictor) Model · Tabular classification ### [wine-quality](https://savrn.com/models/wine-quality-2) [Vova Manannikov](https://savrn.com/model-publishers/vvmnnnkv) No red wine was drunk (unfortunately) while training this model Open weights sklearn [View model](https://savrn.com/models/wine-quality-2) Model · Tabular classification ### [ShopSphere-AICV-TabTransformer-v2](https://savrn.com/models/shopsphere-aicv-tabtransformer-v2) [Mihir Bhavigadda](https://savrn.com/model-publishers/mihirrish) Custom TabTransformer-style PyTorch model for churn prediction, trained on a synthetic ShopSphere e-commerce dataset for an academic Data-Driven Marketing Analytics project. covering Historical / Update / Post-Update periods. Selected on the validation set by maximizing expected net value under the assumption that a missed churner costs 25x more than an unnecessary retention outreach (₹5,000 lost value vs. ₹200 intervention cost) — not by F1. The dataset is synthetic and does not represent real ShopSphere customers. Results, including the baseline comparison, should not be interpreted as causal evidence that the platform algorithm update caused churn, and the hyperparameter search covered a… Open weights pytorch [View model](https://savrn.com/models/shopsphere-aicv-tabtransformer-v2) Model · Tabular classification ### [forex-eurusd-direction](https://savrn.com/models/forex-eurusd-direction) [LUIS VIZCAYA](https://savrn.com/model-publishers/lvizcaya) Binary classification model that predicts whether EUR/USD will close higher (UP) or lower (DOWN) the next trading day. The model uses 53 features including: - Williams %R, CCI: Additional momentum indicators See predict.py for a complete inference example. Based on published financial ML literature: This model is for research and educational purposes only. It is NOT financial advice. Forex trading involves significant risk. Past performance does not guarantee future results. Realistic accuracy for daily direction prediction is 52-56% (literature consensus). This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub. Open weights apache-2.0 [View model](https://savrn.com/models/forex-eurusd-direction) Model · Tabular classification ### [imdb](https://savrn.com/models/imdb) [Devang Parekh](https://savrn.com/model-publishers/de-waang) Problem type: Multi-class Classification; Model ID: 1530155186; CO2 Emissions (in grams): 0.0186; Loss: 0.694; Accuracy: 0.487; Macro F1: 0.218. Open weights transformers [View model](https://savrn.com/models/imdb) Model · Tabular classification ### [heart_failure_prediction](https://savrn.com/models/heart-failure-prediction) [Abdalla Ahmed](https://savrn.com/model-publishers/abdalla732) A Keras / TensorFlow neural network that predicts the presence of heart disease in patients using 11 clinical and demographic features. Educational and research purposes only. Explore how clinical features relate to heart disease risk. - Not a medical device. Do not use for real clinical decisions. - Not validated on real-world hospital populations. from huggingfacehub import hfhubdownload import joblib import pandas as pd from tensorflow import keras modelpath = hfhubdownload("abdalla732/heartfailureprediction", "heartmodel.keras") scalerpath = hfhubdownload("abdalla732/heartfailureprediction", "scaler.joblib") colspath = hfhubdownload("abdalla732/heartfailureprediction"… Open weights mit keras [View model](https://savrn.com/models/heart-failure-prediction) Model · Tabular classification ### [credlayer-solana-fraud-gnn](https://savrn.com/models/credlayer-solana-fraud-gnn) [Ritesh Das](https://savrn.com/model-publishers/ritesh-das) A hybrid Graph Neural Network (GraphSAGE + GATv2) trained on labeled Solana blockchain datasets (SolRPDS, Kaggle Solana, Solarchive) to detect malicious liquidity pools, rug-pull tokens, and fraudulent wallet flows. 1. SolRPDS (Solana Rug Pull Dataset): 62,895 suspicious liquidity pools and 22,195 confirmed rug-pull tokens derived from 3.69 billion transactions. 2. Kaggle Solana Blockchain Dataset: Labeled entity categorization. 3. Solarchive: Partitioned daily Solana Parquet transaction flows. Open weights mit [View model](https://savrn.com/models/credlayer-solana-fraud-gnn) Model · Tabular classification ### [collaborative-filtering-movielens](https://savrn.com/models/collaborative-filtering-movielens) [Keras](https://savrn.com/model-publishers/keras-io) This repo contains the model and the notebook on how to build and train a Keras model for Collaborative Filtering for Movie Recommendations. Full credits to Siddhartha Banerjee. Based on a user and movies they have rated highly in the past, this model outputs the predicted rating a user would give to a movie they haven't seen yet (between 0-1). This information can be used to find out the top recommended movies for this user. The dataset consists of user's ratings on specific movies. It also consists of the movie's specific genres. The model was trained for 5 epochs with a batch size of 64. The following hyperparameters were used during training: - trainingprecision: float32 Open weights cc0-1.0 tf-keras [View model](https://savrn.com/models/collaborative-filtering-movielens) Model · Tabular classification ### [human-disease-prediction](https://savrn.com/models/human-disease-prediction) [AWeirdDev](https://savrn.com/model-publishers/aweirddev) Try it on Spaces The yourdata variable should be a vector of zeros and ones. A zero means "False," and a one means "True." Create a vector that pairs with the following symptoms, then the model will predict what disease it might be. It has been reported as 1.0 (100%), but I don't believe it. Open weights mit sklearn [View model](https://savrn.com/models/human-disease-prediction) Model · Tabular classification ### [nanites-fiorino-tabular](https://savrn.com/models/nanites-fiorino-tabular) [Nanites](https://savrn.com/model-publishers/nanite-labs) nano quattrocento tabular fondamento model with synthetic and real-data priors. Tabular in-context-learning model, ~4.5M params: labeled context rows in, query-row predictions out, one forward pass, no fine-tuning. A nano lab build (single 8GB GPU) — priors and efficiency over volume: 226,000 tables in the record run (≈400,000 across the lineage) vs 100,000,000+ at the big labs. Pretrained on real historical ledger tasks (Borromei, ICMA Crown loans, Bristol customs, Irish Exchequer — 30,514 rows / 460 tasks, plus audit-passed derived value-standing tasks) and a world-profiled synthetic diet (linear/additive, smooth, piecewise/threshold, tree, interaction, heteroskedastic worlds + NanoTabICL… Open weights mit pytorch [View model](https://savrn.com/models/nanites-fiorino-tabular) Model · Tabular classification ### [BAAR4-guard](https://savrn.com/models/baar4-guard) [BAAR](https://savrn.com/model-publishers/aixk) 이 저장소는 2017~2026 전주기 트래픽(CIC-IDS2017, CICDDoS2019, CICIoT2023, 2024~2026 AI Vectors)으로 훈련된 고속 인라인 AI 보안 방화벽 엔진입니다. 1. model.safetensors: PyTorch SafeTensors 가중치 2. model.onnx: WebAssembly 및 에지 런타임용 고속 ONNX 그래프 3. modelguardultrafp16.baar3: Zero-Copy Direct-mmap FP16 초고속 커널 바이너리 4. config.json: Robust 스케일러 및 제로 트러스트 임계치 메타데이터 Open weights apache-2.0 644,381 parameters [View model](https://savrn.com/models/baar4-guard) Model · Tabular classification ### [badak](https://savrn.com/models/badak) [Arif Akbarul Huda](https://savrn.com/model-publishers/omayib) Open weights cc-by-nc-nd-4.0 scikit-learn [View model](https://savrn.com/models/badak) Model · Tabular classification ### [tourism-model](https://savrn.com/models/tourism-model) [Isaiah Kofi Tefutor](https://savrn.com/model-publishers/istefutor) XGBoost classification pipeline selected by five-fold stratified grid search using F1. The target represents historical general tourism package purchases. Open weights scikit-learn [View model](https://savrn.com/models/tourism-model) Model · Tabular classification ### [tourism-wellness-model](https://savrn.com/models/tourism-wellness-model) [ShrimathiNarayanachar](https://savrn.com/model-publishers/shrimathin) Open weights mit [View model](https://savrn.com/models/tourism-wellness-model) Model · Tabular classification ### [transfer-fraud-model](https://savrn.com/models/transfer-fraud-model) [Youssef Mlaouhia](https://savrn.com/model-publishers/yssfmlha) Gradient-boosted classifier. You compute the 15 features yourself and pass them in; the model returns P(fraud) and a risk level 0-3. Trained on a synthetic dataset - validate on real data. predict accepts one dict, a list of dicts, or a pandas DataFrame with these columns (extra columns are ignored, order doesn't matter, missing ones raise an error). "History" = the sender's transfers strictly before the one being scored, within the last 180 days. "rocauctest": 0.9924, "prauctest": 0.8382, "fraudratetest": 0.0169, "alertprecisionlevel2plus": 0.64, "alertrecalllevel2plus": 0.8287, "recalllevel1plus": 0.9655 Open weights mit sklearn [View model](https://savrn.com/models/transfer-fraud-model) Model · Tabular classification ### [xcross-attempt-v1](https://savrn.com/models/xcross-attempt-v1) [(Ministry of) Silly Kicks](https://savrn.com/model-publishers/silly-kicks) XCrossAttemptModel is a deterministic-XGBoost classifier estimating P(the in-possession team attempts a cross within ~1 s of a tracking frame) — a STATE-anchored framing, reframed from the sender-level event treatment in Cao et al. (arXiv:2505.11841). It carries 7 of the paper's 8 confounders (crosser-position, #7, is omitted — no faithful tracking-only proxy) plus a novel, isolatable GK-position confounder block, which is the paper's headline gap and the reason this model exists inside the GKDV research arc (TF-17 → TF-19). - 16 features, faithful (velocity-bearing), goal-relative coordinates via the shared geometry helper - The scextended model is fit on the owner-tier corpus (IDSSE +… Open weights mit silly-kicks [View model](https://savrn.com/models/xcross-attempt-v1) Model · Tabular classification ### [xshot-occurrence-v1](https://savrn.com/models/xshot-occurrence-v1) [(Ministry of) Silly Kicks](https://savrn.com/model-publishers/silly-kicks) XShotOccurrenceModel is a deterministic-XGBoost classifier estimating P(a shot is attempted by the in-possession team within ~1 s of a tracking frame) — the xS surface of the GKDV research arc (TF-16). Paper-faithful 27-feature extractor in goal-relative coordinates via the shared geometry helper: ball r/θ/z/speed, an openGoal goal-mouth obstruction term, GK distance/bearing, and the 5 nearest defenders + 5 nearest attackers. - Trained on 964,263 rows / 182,517 positives (18.9% positive rate) scextended is HF-only for licensing, not quality: it is trained on restricted owner-tier SkillCorner data that cannot be redistributed inside the PyPI wheel (ADR-038). Only learned parameters are… Open weights mit silly-kicks [View model](https://savrn.com/models/xshot-occurrence-v1) ## Questions ### Which Tabular classification models are most downloaded? By monthly downloads reported by the Hugging Face Hub: mitra-classifier (283.4k); sap-rpt-1-oss (123.8k); TabSTAR (62.7k). ## Other Tasks - [Text Generation](https://savrn.com/models/tasks/text-generation) 1598 - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 598 - [Robotics](https://savrn.com/models/tasks/robotics) 410 - [Feature Extraction](https://savrn.com/models/tasks/feature-extraction) 405 - [Text Classification](https://savrn.com/models/tasks/text-classification) 336 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 239 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 190 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 149 - [Image Classification](https://savrn.com/models/tasks/image-classification) 140 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 105 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 [See all](https://savrn.com/models/tasks)