TomasrRodrigues/TinyGPT

A research-grade PyTorch implementation of a decoder-only transformer from scratch, designed for experimentation on small-scale GPT models (0.5M–5M parameters). Includes full training loop, modular architecture, and tools for analyzing attention, embeddings, and scaling behavior.

21
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

MIT

Category

transformer-architecture-education

Last pushed

Mar 13, 2026

Commits (30d)

0

GitHub
Transformer Architecture Education · 63 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TomasrRodrigues/TinyGPT"

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

Higher-rated alternatives

huggingface/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in...

87

kyegomez/LongNet

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

51

pbloem/former

Simple transformer implementation from scratch in pytorch. (archival, latest version on codeberg)

49

NVIDIA/FasterTransformer

Transformer related optimization, including BERT, GPT

48

kyegomez/SimplifiedTransformers

SimplifiedTransformer simplifies transformer block without affecting training. Skip connections,...

47

Explore Transformer Models

All categories Trending Transformer directory Insights