The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Process" (arxiv 2407.20311) and "Physics of Language Models Part 2.2, How to Learn From Mistakes on Grade-School Math Problems" (arxiv 2408.16293)
☆84Jan 12, 2025Updated last year
Alternatives and similar repositories for iGSM
Users that are interested in iGSM are comparing it to the libraries listed below
Sorting:
- ☆20Nov 3, 2024Updated last year
- This is the source code of FUSION, a safety-aware causal representation for generalizable driving agents.☆26Oct 23, 2024Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Jan 23, 2024Updated 2 years ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Jul 17, 2025Updated 7 months ago
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆322Jan 5, 2026Updated 2 months ago
- The evaluation framework for training-free sparse attention in LLMs☆121Jan 27, 2026Updated last month
- M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models☆46Jul 17, 2025Updated 7 months ago
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆38Feb 27, 2024Updated 2 years ago
- ☆10Oct 11, 2022Updated 3 years ago
- flex-block-attn: an efficient block sparse attention computation library☆124Dec 26, 2025Updated 2 months ago
- [NeurIPS 2024] "Discovery of the Hidden World with Large Language Models"☆28Dec 2, 2024Updated last year
- Functional Optimal Transport: Map Estimation and Domain Adaptation for Functional data☆27Jun 7, 2021Updated 4 years ago
- The official repository for the CodeGym project: "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym"☆23Oct 14, 2025Updated 4 months ago
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆21Feb 19, 2026Updated 2 weeks ago
- ☆55Aug 5, 2025Updated 7 months ago
- ☆16Jan 5, 2025Updated last year
- Feasibility Consistent Representation Learning for Safe Reinforcement Learning (ICML 2024). Current SOTA model-free safe RL algorithm on …☆14Jul 12, 2024Updated last year
- ☆36Feb 26, 2024Updated 2 years ago
- Adversarially Robust Generalization Just Requires More Unlabeled Data☆11Aug 8, 2019Updated 6 years ago
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆14Aug 25, 2023Updated 2 years ago
- ☆56Sep 17, 2025Updated 5 months ago
- Train and visualise a latent variable model of moving objects.☆16Apr 28, 2020Updated 5 years ago
- Codebase for Math Neurosurgery: Isolating LLMs' Math Reasoning Abilities Using Only Forward Passes☆21Jun 15, 2025Updated 8 months ago
- ☆16Dec 12, 2024Updated last year
- Implementation of the Playground environment from the paper Language as a Cognitive Tool to Imagine Goals inCuriosity-Driven Exploration.☆11Mar 5, 2021Updated 5 years ago
- ☆33Dec 9, 2022Updated 3 years ago
- ☆35Jun 15, 2023Updated 2 years ago
- Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without…☆21Mar 15, 2025Updated 11 months ago
- This code accompanies the paper "Information-Theoretic Probing for Linguistic Structure" published in ACL 2020.☆21Apr 27, 2020Updated 5 years ago
- Source code for "Sub-sampled Cubic Regularization for Non-convex Optimization", JM Kohler, A Lucchi, https://arxiv.org/abs/1705.05933☆16Dec 12, 2018Updated 7 years ago
- ☆71Oct 16, 2024Updated last year
- Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers☆28Mar 1, 2025Updated last year
- LLM training in simple, raw C/CUDA☆15Dec 5, 2024Updated last year
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19May 8, 2025Updated 9 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆273Apr 26, 2024Updated last year
- LoFiT: Localized Fine-tuning on LLM Representations☆44Jan 15, 2025Updated last year
- Code and data for paper "(How) do Language Models Track State?"☆20Mar 31, 2025Updated 11 months ago
- Learning to Model Editing Processes☆26Aug 3, 2025Updated 7 months ago
- Open source code combining implementations of Upside Down Reinforcement Learning and Reward Conditioned Policies☆19Mar 10, 2021Updated 4 years ago