AdityaNG/kan-gpt

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

51
/ 100
Established

This project offers a Python implementation for building language models, specifically Generative Pre-trained Transformers (GPTs), using a different type of neural network called Kolmogorov-Arnold Networks (KANs). It takes in text data and can generate new, coherent text based on the patterns it learned. This tool is designed for researchers and machine learning engineers who are exploring novel neural network architectures for natural language processing.

725 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a machine learning researcher or engineer interested in experimenting with KANs for language generation and want to compare their performance against traditional MLP-based GPT models.

Not ideal if you are looking for a ready-to-use, production-grade language model for immediate deployment or if you are not comfortable with advanced machine learning development.

natural-language-processing machine-learning-research deep-learning-architecture text-generation neural-network-development
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

725

Forks

55

Language

Python

License

MIT

Last pushed

Nov 25, 2024

Commits (30d)

0

Dependencies

12

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/AdityaNG/kan-gpt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.