danieldeutsch/repro

Repro is a library for easily running code from published papers via Docker.

46
/ 100
Emerging

This tool helps researchers and practitioners use pre-trained AI models from academic papers without dealing with complex setup. You input text or data, and it outputs predictions or evaluations from those models. It's designed for anyone who wants to apply advanced AI models to their work without deep technical expertise in machine learning environments.

No commits in the last 6 months. Available on PyPI.

Use this if you need to quickly run and evaluate state-of-the-art AI models from research papers, especially for tasks like text summarization or question answering, without worrying about dependency conflicts or environment setup.

Not ideal if you need to fine-tune these models, develop new models, or if you don't have Docker installed and prefer not to use it.

natural-language-processing research-reproducibility text-summarization question-answering model-evaluation
Stale 6m
Maintenance 0 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

42

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Sep 22, 2023

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danieldeutsch/repro"

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