idrori / mathQ
Data and code for the paper "A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level" by Drori et al., 2022.
☆185Updated 2 years ago
Alternatives and similar repositories for mathQ:
Users that are interested in mathQ are comparing it to the libraries listed below
- ☆252Updated 2 years ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆629Updated last year
- ☆180Updated last year
- The MATH Dataset (NeurIPS 2021)☆983Updated 5 months ago
- Formal to Formal Mathematics Benchmark☆325Updated last year
- ☆159Updated 9 months ago
- Automatic gradient descent☆206Updated last year
- Language Modeling with the H3 State Space Model☆516Updated last year
- ☆514Updated 11 months ago
- ☆368Updated 3 years ago
- Benchmark for undergraduate-level formal mathematics☆97Updated 3 months ago
- A hard gym for programming☆145Updated 6 months ago
- Tutorial on neural theorem proving☆164Updated last year
- ChatGPT plugin for theorem proving in Lean☆115Updated 9 months ago
- ☆164Updated last year
- Code for Parsel 🐍 - generate complex programs with language models☆420Updated last year
- ☆699Updated last year
- Resources of deep learning for mathematical reasoning (DL4MATH).☆345Updated last year
- An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"☆300Updated 4 months ago
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆288Updated last year
- LLMs + Lean, on your laptop or in the cloud☆132Updated 2 months ago
- Retrieval-Augmented Theorem Provers for Lean☆242Updated 4 months ago
- Reflexion: an autonomous agent with dynamic memory and self-reflection☆384Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆461Updated 7 months ago
- Puzzles for exploring transformers☆331Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆182Updated 7 months ago
- This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (Neur…☆504Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆192Updated last week
- ☆118Updated 2 months ago
- Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"☆203Updated last year