Metadata-Version: 2.4
Name: langspace
Version: 0.3.4
Summary: LangSpace: Probing Large Language VAEs made simple
Home-page: 
Author: ['Danilo S. Carvalho', 'Yingji Zhang']
Author-email: "Danilo S. Carvalho" <danilo.carvalho@manchester.ac.uk>, Yingji Zhang <yingji.zhang@postgrad.manchester.ac.uk>
Project-URL: Homepage, https://github.com/neuro-symbolic-ai/LangSpace
Project-URL: Issues, https://github.com/neuro-symbolic-ai/LangSpace/issues
Keywords: probing,vae,llm,generative,nlp
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.4
Requires-Dist: numpy>=1.26.4
Requires-Dist: transformers>=4.48.0
Requires-Dist: pandas>=2.2.3
Requires-Dist: scipy>=1.13.1
Requires-Dist: gensim>=4.3.3
Requires-Dist: pot==0.9.3
Requires-Dist: yellowbrick==1.5
Requires-Dist: langvae>=0.6.6
Requires-Dist: saf-nlp>=0.5.5
Requires-Dist: saf-datasets>=0.6.16
Dynamic: author
Dynamic: license-file

# LangSpace: Probing Large Language VAEs made simple

LangSpace is a Python library for evaluating and probing language models using Variational Autoencoders (VAEs). It provides an easy-to-use interface to perform a variety of analises on pretrained [LangVAE](https://github.com/neuro-symbolic-ai/LangVAE) models.

## Installation

To install LangSpace, simply run:

```bash
pip install langspace
```

This will install all necessary dependencies and set up the package for use in your Python projects.

## Usage

TBC


## License

LangVAE is licensed under the GPLv3 License. See the LICENSE file for details.
