softsys4ai/differentiable-proving
Code and data for the paper "Pretrained Language Models are Symbolic Mathematics Solvers too!", arXiv:2110.03501
This project helps machine learning researchers fine-tune large language models to solve symbolic mathematics problems. It takes a pre-trained language model and specialized symbolic math datasets as input, producing a fine-tuned model capable of accurately solving algebraic equations, calculus problems, and more. It is designed for AI researchers working on advancing language model capabilities in mathematical reasoning.
No commits in the last 6 months.
Use this if you are an AI researcher looking to explore or implement language models for symbolic mathematics tasks.
Not ideal if you are a mathematician looking for a ready-to-use tool to solve math problems without needing to fine-tune models.
Stars
12
Forks
2
Language
Python
License
MIT
Category
Last pushed
Nov 23, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/softsys4ai/differentiable-proving"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.