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-weight model · Tabular classification
DataScientst-models
by ALİ OKTAY BBUS OKTAYBBS/DataScientst-models
Trained models from a comprehensive ML/AI portfolio spanning 10 categories. All models were trained on real Kaggle datasets.
Parameters—
Context—
Weights340.2 MB
Licensemit
AccessOpen weights
Monthly Downloads687
Model Card
By ALİ OKTAY BBUS, published under mit, revision c40104b6f379.
Trained models from a comprehensive ML/AI portfolio spanning 10 categories. All models were trained on real Kaggle datasets.
Read ALİ OKTAY BBUS's full model card
DataScientst -- 30 Projects, 34 Trained Models
Trained models from a comprehensive ML/AI portfolio spanning 10 categories. All models were trained on real Kaggle datasets.
Repository Structure
regression/ -- Gold, Student, Uber prediction models
classification/ -- Mobile, Wine, Churn classification models
clustering/ -- NBA, Credit Card, Spotify clustering models + scalers
computer_vision/ -- Face mask detection model
nlp/ -- Spam, IMDb, Fake News models + TF-IDF vectorizers
recommendation/ -- Movie, Book, Music recommendation data + similarity matrices
time_series/ -- Stock, Weather, Store prediction models
data_viz/ -- Visualization CSV datasets
deep_learning/ -- CNN models (Keras) + Markov text generator
metrics/ -- Performance metrics for all models (JSON, CSV, PNG)
Models & Metrics
Regression
| Model | File | Metric |
|---|---|---|
| Gold Price Prediction | regression/gold_model.pkl |
R² = 0.990 |
| Student Exam Score | regression/student_model.pkl |
R² = 0.849 |
| Uber/Taxi Fare | regression/uber_model.pkl |
R² = 0.778 |
Classification
| Model | File | Metric |
|---|---|---|
| Mobile Price Segment | classification/mobile_model.pkl |
Accuracy = 81.2% |
| Wine Quality | classification/wine_model.pkl |
Accuracy = 67.5% |
| Customer Churn | classification/churn_model.pkl |
Accuracy = 78.9% |
Clustering
| Model | File | Metric |
|---|---|---|
| NBA Player Clustering | clustering/nba_model.pkl |
Silhouette = 0.452 |
| Credit Card Segmentation | clustering/cc_model.pkl |
Silhouette = 0.531 |
| Spotify Song Clustering | clustering/spotify_model.pkl |
Silhouette = 0.327 |
NLP
| Model | File | Metric |
|---|---|---|
| SMS Spam Detection | nlp/spam_model.pkl |
Accuracy = 98.0% |
| IMDb Sentiment Analysis | nlp/imdb_model.pkl |
Accuracy = 87.3% |
| Fake News Detection | nlp/news_model.pkl |
Accuracy = 97.6% |
Deep Learning
| Model | File | Metric |
|---|---|---|
| Pneumonia Detection (CNN) | deep_learning/pneumonia_model.keras |
Val Acc = 92.5% |
| Facial Emotion Recognition (CNN) | deep_learning/fer_model.keras |
Val Acc = 65.4% |
Usage
from huggingface_hub import hf_hub_download
import joblib
# Download from a category folder
model_path = hf_hub_download(
repo_id="OKTAYBBS/DataScientst-models",
filename="regression/gold_model.pkl"
)
model = joblib.load(model_path)
prediction = model.predict([[1500, 70, 20, 1.1]])
# For Keras models
import tensorflow as tf
model_path = hf_hub_download(
repo_id="OKTAYBBS/DataScientst-models",
filename="deep_learning/pneumonia_model.keras"
)
model = tf.keras.models.load_model(model_path)
Links
- Live Demo: Streamlit App
- Portfolio: HF Space
- Source Code: GitHub
Identity and Version
- Repository
- OKTAYBBS/DataScientst-models
- Publisher
- ALİ OKTAY BBUS
- Task
- Tabular classification
- Modality
- Tabular
- Library
- keras
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- c40104b6f379f3bc7a0f5d000cdf35fa8caf9467
- First published
- 2026-08-19
- Last updated
- 2026-08-19
Files and Weights
42 files, 340.2 MB in total.
Configuration1 file · 4.0 KB
Documentation1 file · 3.3 KB
Other39 files · 340.2 MB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| metrics/metrics.json | Configuration | 4.0 KB | — |
| README.md | Documentation | 3.3 KB | — |
| classification/churn_model.pkl | Other | 39.3 MB | 746ebfaca9bf |
| classification/mobile_model.pkl | Other | 4.4 MB | c60dd168fb9a |
| classification/wine_model.pkl | Other | 21.6 MB | 83128a83c9ec |
| clustering/cc_model.pkl | Other | 35.4 KB | 17a15041cbe1 |
| clustering/cc_scaler.pkl | Other | 959 B | 4bea32d2828b |
| clustering/nba_model.pkl | Other | 44.8 KB | 8c1a02d93070 |
| clustering/nba_scaler.pkl | Other | 943 B | d49d120df98c |
| clustering/spotify_model.pkl | Other | 456.8 KB | 053d51c550de |
| clustering/spotify_scaler.pkl | Other | 959 B | 4cd7f4589430 |
| computer_vision/mask_model.pkl | Other | 384.5 KB | b43ae4348e14 |
| data_viz/co2_emissions_viz.csv | Other | 8.8 KB | — |
| data_viz/ecommerce_viz.csv | Other | 61.2 KB | — |
| data_viz/social_media_viz.csv | Other | 15.1 KB | — |
| deep_learning/fer_model.keras | Other | 8.3 MB | 322562c347f1 |
| deep_learning/pneumonia_model.keras | Other | 12.9 MB | 51aa84a58243 |
| deep_learning/text_robot_model.pkl | Other | 1.2 KB | 7c895025b971 |
| metrics/metrics_summary.csv | Other | 836 B | — |
| metrics/metrics_summary.png | Other | 51.1 KB | — |
| nlp/imdb_model.pkl | Other | 40.9 KB | c681b38ec466 |
| nlp/imdb_vectorizer.pkl | Other | 183.1 KB | c030ebf65d3c |
| nlp/news_model.pkl | Other | 40.9 KB | 462fd956d419 |
| nlp/news_vectorizer.pkl | Other | 184.7 KB | a3514cbb03c9 |
| nlp/spam_model.pkl | Other | 96.8 KB | 05bb1fad7820 |
| nlp/spam_vectorizer.pkl | Other | 107.4 KB | db28fca0fcea |
| recommendation/book_data.pkl | Other | 91.6 KB | 28c6940982d4 |
| recommendation/book_similarity.pkl | Other | 18.0 MB | 9afe193530f0 |
| recommendation/movie_data.pkl | Other | 28.3 KB | 3fa03a9aec27 |
| recommendation/movie_similarity.pkl | Other | 17.8 MB | c1fa10061e47 |
| recommendation/song_data.pkl | Other | 46.8 KB | f76e309722f3 |
| recommendation/song_similarity.pkl | Other | 18.0 MB | 7655e45335cf |
| regression/gold_model.pkl | Other | 33.3 MB | c6a9c1f3281c |
| regression/student_model.pkl | Other | 3.2 MB | 470e16e64b18 |
| regression/uber_model.pkl | Other | 161.6 MB | e6d97fd74f34 |
| time_series/stock_model.pkl | Other | 817 B | f4b075ae90cb |
| time_series/stock_recent.pkl | Other | 465 B | 8ad9b1029cba |
| time_series/walmart_model.pkl | Other | 817 B | 7d49d7fab47a |
| time_series/walmart_recent.pkl | Other | 345 B | 329c8a50594e |
| time_series/weather_model.pkl | Other | 817 B | e14a41f67d4f |
| time_series/weather_recent.pkl | Other | 465 B | c5a29b65eb29 |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
Download from ALİ OKTAY BBUS
Released by ALİ OKTAY BBUS through its official repository on Hugging Face. Read the license.
Questions About DataScientst-models
Can I use DataScientst-models commercially?
Yes. DataScientst-models is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
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…