SauravP97/toy-transformer

A decoder only Transformer implementing masked attention

24
/ 100
Experimental

This project helps you train a small language model on your own text data and then generate new text from it, right on your local machine. You feed in a block of text, and it produces a trained model that can generate coherent continuations based on the patterns it learned from your input. It's designed for anyone interested in experimenting with text generation or understanding how basic language models work, without needing specialized hardware.

Use this if you want to train a small text-generating AI on your own documents and create new content or explore basic AI language models without requiring a powerful GPU.

Not ideal if you need a high-performance, production-ready language model, or if you plan to work with very large datasets or complex, nuanced text generation tasks.

text-generation natural-language-processing creative-writing content-creation machine-learning-experimentation
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Python

License

MIT

Last pushed

Jan 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SauravP97/toy-transformer"

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