zhjgao/difformer

The official codebase for "Empowering Diffusion Models on the Embedding Space for Text Generation" (NAACL 2024)

36
/ 100
Emerging

This project helps machine learning engineers and researchers generate human-like text by training diffusion models on existing text data. It takes raw text datasets, preprocesses them, and then outputs a trained model capable of generating new text for tasks like translation or question paraphrasing. This tool is for those building and experimenting with advanced natural language generation systems.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher focused on developing and evaluating state-of-the-art text generation models, particularly those leveraging diffusion techniques.

Not ideal if you need an out-of-the-box text generation solution without extensive machine learning development or model training.

natural-language-generation machine-translation text-summarization text-paraphrasing generative-ai-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

56

Forks

7

Language

Python

License

MIT

Last pushed

Apr 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zhjgao/difformer"

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