hkust-nlp/dart-math

[NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*

35
/ 100
Emerging

This project helps developers improve how their AI models solve mathematical problems. By using a 'difficulty-aware' training approach, it takes mathematical problems and solutions as input and produces a more accurate and robust AI model for math problem-solving. It's designed for AI/ML developers or researchers who build and fine-tune large language models for complex reasoning tasks.

121 stars. No commits in the last 6 months.

Use this if you are an AI/ML developer looking to create more accurate and robust language models for mathematical problem-solving, especially for challenging or diverse math datasets.

Not ideal if you are looking for a pre-built, end-user application to solve math problems directly, as this is a framework for training underlying AI models.

AI model training mathematical reasoning large language models algorithm development data science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

121

Forks

7

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hkust-nlp/dart-math"

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