RobinKa/discrete-flow-matching-pytorch

Discrete Flow Matching implemented in PyTorch

29
/ 100
Experimental

This project helps machine learning researchers and practitioners generate discrete data, such as text, using a method called Discrete Flow Matching. You provide an initial configuration, and it outputs a trained model capable of creating new text sequences. It's designed for those experimenting with advanced generative models beyond typical continuous data approaches.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer exploring cutting-edge generative models for discrete data like text, especially if you're working with PyTorch.

Not ideal if you need a plug-and-play solution for text generation without deep understanding of model training or if you are not comfortable with Python and PyTorch.

generative-AI text-generation machine-learning-research discrete-data-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

35

Forks

2

Language

Python

License

MIT

Last pushed

Mar 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RobinKa/discrete-flow-matching-pytorch"

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