Metadata-Version: 2.4
Name: coldread-tfm
Version: 0.1.2
Summary: ColdRead tabular foundation model inference for classification and regression
Author: ColdRead contributors
License-Expression: Apache-2.0
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Science/Research
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.2
Requires-Dist: numpy>=1.24
Requires-Dist: pydantic>=2
Requires-Dist: safetensors>=0.4
Requires-Dist: huggingface-hub>=0.25
Provides-Extra: test
Requires-Dist: pytest>=8; extra == "test"
Requires-Dist: scikit-learn>=1.3; extra == "test"
Provides-Extra: hub
Dynamic: license-file

# ColdRead TFM

ColdRead is a new, small tabular foundation model for classification and regression, developed using a new approach to model training.

## Installation

```bash
pip install coldread-tfm
```

## Classification

```python
from coldread import ColdReadClassifier

model = ColdReadClassifier.from_pretrained("msalem7777/coldread-classification-v0.1")
model.fit(X_train, y_train)
predictions = model.predict(X_test)
probabilities = model.predict_proba(X_test)
```

## Regression

```python
from coldread import ColdReadRegressor

model = ColdReadRegressor.from_pretrained("msalem7777/coldread-regression-v0.1")
model.fit(X_train, y_train)
predictions = model.predict(X_test)
```

## License

Apache-2.0.
