Metadata-Version: 2.1
Name: predacons
Version: 0.0.120
Summary: A python library based on transformers for transfer learning
Home-page: https://github.com/shouryashashank/predacons
Author: shouryashashank
Author-email: shouryashashank@gmail.com
License: AGPLv3+
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Classifier: Programming Language :: Python :: 3.10
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE-AGPL
License-File: LICENSE-COMMERCIAL-PERPETUAL
License-File: LICENSE-COMMERCIAL-YEARLY
Requires-Dist: bson>=0.5.10
Requires-Dist: pandas>=1.5.3
Requires-Dist: numpy>=1.24.1
Requires-Dist: regex>=2021.4.4
Requires-Dist: PyPDF2>=3.0.1
Requires-Dist: docx>=0.2.4
Requires-Dist: python-docx>=1.0.1
Requires-Dist: transformers>=4.29.1
Requires-Dist: einops>=0.7.0
Requires-Dist: openai>=1.12.0
Requires-Dist: typing-extensions>=4.9.0
Requires-Dist: peft>=0.8.2
Requires-Dist: trl>=0.8.1
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: twine>=4.0.2; extra == "dev"

# Predacons
Predacons is a Python library based on transformers used for transfer learning. It offers a suite of tools for data processing, model training, and text generation, making it easier to apply advanced machine learning techniques to your projects.

![PyPI](https://img.shields.io/pypi/v/predacons)   ![Downloads](https://img.shields.io/pypi/dm/predacons)   ![License](https://img.shields.io/pypi/l/predacons)   ![Python Version](https://img.shields.io/pypi/pyversions/predacons)

## Installation
To install Predacons, use the following pip command:
```bash
pip install predacons
```

## Usage
Here's a quick start guide to using Predacons in your Python projects:

```python
from predacons import predacons

# Initialize the library
predacons.rollout()

# Load documents from a directory
predacons.read_documents_from_directory('your/directory/path')

# Clean text data
cleaned_text = predacons.clean_text("Your dirty text here")

# Train a model with your data
predacons.train(train_file_path="path/to/train/file",
                model_name="your_model_name",
                output_dir="path/to/output/dir",
                overwrite_output_dir=True,
                per_device_train_batch_size=4,
                num_train_epochs=3,
                save_steps=100)

# Generate text using a trained model
generated_text = predacons.generate_text(model_path="path/to/your/model",
                                         sequence="Seed text for generation",
                                         max_length=50)
```

## Features
Predacons provides a comprehensive set of features for working with transformer models, including:

- **Data Loading**: Easily load data from directories or files.
- **Text Cleaning**: Clean your text data with built-in functions.
- **Model Training**: Train transformer models with custom data.
- **Text Generation**: Generate text using trained models.

## Contributing
Contributions to the Predacons library are welcome! If you have suggestions for improvements or new features, please open an issue first to discuss your ideas. For code contributions, please submit a pull request.

## License

This project is licensed under multiple licenses:

- For **free users**, the project is licensed under the terms of the GNU Affero General Public License (AGPL). See  [`LICENSE-AGPL`](LICENSE-AGPL) for more details.

- For **paid users**, there are two options:
    - A perpetual commercial license. See [`LICENSE-COMMERCIAL-PERPETUAL`](LICENSE-COMMERCIAL-PERPETUAL) for more details.
    - A yearly commercial license. See [`LICENSE-COMMERCIAL-YEARLY`](LICENSE-COMMERCIAL-YEARLY) for more details.

Please ensure you understand and comply with the license that applies to you.

