kamalkraj/minGPT-TF

A minimal TF2 re-implementation of the OpenAI GPT training

43
/ 100
Emerging

This project helps machine learning practitioners or researchers understand and implement the core components of GPT-like models using TensorFlow. It takes a sequence of numerical tokens (representing text or other discrete data) and outputs a probability distribution for the next token in the sequence. Data scientists, AI researchers, or students learning about generative models would find this useful for experimenting with foundational transformer architectures.

No commits in the last 6 months.

Use this if you want a clear, minimal, and educational implementation of a GPT model's training process in TensorFlow.

Not ideal if you need to train very large-scale GPT-3 like models that require extensive distributed training and memory management beyond typical GPU limits.

natural-language-generation text-prediction transformer-models sequence-modeling machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

58

Forks

18

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 01, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/kamalkraj/minGPT-TF"

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