kabachuha/nanoGPKANT

Testing KAN-based text generation GPT models

27
/ 100
Experimental

This project offers a testing ground for those curious about experimental text generation models, specifically those combining Generative Pretrained Transformers (GPTs) with Kolmogorov-Arnold Networks (KANs). You can feed it text, like Shakespearean plays, and it will generate new text in a similar style. This is for researchers and developers exploring novel architectures for large language models.

No commits in the last 6 months.

Use this if you are an AI researcher or developer actively experimenting with and comparing the performance of new neural network architectures, particularly KAN-based transformers, for text generation.

Not ideal if you need a production-ready text generation model or are looking for a tool to generate high-quality, coherent text quickly, as this is an early-stage research prototype.

AI-research natural-language-generation neural-network-architecture machine-learning-experimentation transformer-models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

May 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kabachuha/nanoGPKANT"

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