Shengyu-Feng/TSMC4MATH
[ICLR2025] Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo (https://arxiv.org/abs/2410.01920)
This project helps machine learning researchers improve how language models solve complex math problems. It takes a base language model and a dataset of math problems, then trains the model to generate accurate, step-by-step reasoning. The output is a more capable language model specifically tuned for mathematical problem-solving.
No commits in the last 6 months.
Use this if you are an AI/ML researcher or practitioner looking to enhance large language models' ability to perform multi-step mathematical reasoning.
Not ideal if you are looking for an off-the-shelf math solver or do not have experience with model training and fine-tuning.
Stars
5
Forks
—
Language
Python
License
—
Category
Last pushed
May 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Shengyu-Feng/TSMC4MATH"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ExtensityAI/symbolicai
A neurosymbolic perspective on LLMs
TIGER-AI-Lab/MMLU-Pro
The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding...
MMMU-Benchmark/MMMU
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal...
deep-symbolic-mathematics/LLM-SR
[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation...
ise-uiuc/magicoder
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct