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)
☆88Jan 12, 2025Updated last year
Alternatives and similar repositories for iGSM
Users that are interested in iGSM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2024] "Mind the Gap between Prototypes and Images in Cross-domain Finetuning"☆11Nov 15, 2024Updated last year
- ☆20Nov 3, 2024Updated last year
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆354May 20, 2026Updated last month
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆92Jul 17, 2025Updated 11 months ago
- The evaluation framework for training-free sparse attention in LLMs☆124Jan 27, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆61Sep 17, 2025Updated 9 months ago
- M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models☆48Jul 17, 2025Updated 11 months ago
- Codebase for Math Neurosurgery: Isolating LLMs' Math Reasoning Abilities Using Only Forward Passes☆23Jun 15, 2025Updated last year
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆22Feb 19, 2026Updated 4 months ago
- [NeurIPS 2024] "Discovery of the Hidden World with Large Language Models"☆31Dec 2, 2024Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Jan 23, 2024Updated 2 years ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆240Jul 19, 2025Updated 11 months ago
- ☆34Nov 30, 2025Updated 7 months ago
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆14Aug 25, 2023Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- 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
- ☆26Feb 20, 2026Updated 4 months ago
- Spectral Sphere Optimizer☆119Mar 23, 2026Updated 3 months ago
- [ICML 2026 Spotlight] On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models☆158Jun 8, 2026Updated 3 weeks ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆19May 19, 2019Updated 7 years ago
- ☆63Jun 2, 2026Updated last month
- ☆39Feb 26, 2024Updated 2 years ago
- Benchmarking Optimizers for LLM Pretraining☆60May 3, 2026Updated 2 months ago
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆20Jun 12, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A project designed to build and render a full Minecraft crafting tree.☆10Aug 10, 2021Updated 4 years ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆277Apr 26, 2024Updated 2 years ago
- toy reproduction of Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts☆31Sep 1, 2024Updated last year
- Evaluating Durability: Benchmark Insights into Multimodal Watermarking☆12Jun 7, 2024Updated 2 years ago
- ☆245Aug 14, 2024Updated last year
- ☆10Oct 11, 2022Updated 3 years ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆29Oct 14, 2025Updated 8 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆45Jan 15, 2025Updated last year
- ☆224Dec 23, 2025Updated 6 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Code for "What really matters in matrix-whitening optimizers?"☆24Oct 31, 2025Updated 8 months ago
- ☆16Jul 29, 2025Updated 11 months ago
- Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence☆67Nov 11, 2025Updated 7 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆161Jul 8, 2025Updated 11 months ago
- Adversarially Robust Generalization Just Requires More Unlabeled Data☆11Aug 8, 2019Updated 6 years ago
- Feasibility Consistent Representation Learning for Safe Reinforcement Learning (ICML 2024). Current SOTA model-free safe RL algorithm on …☆17Jul 12, 2024Updated last year
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19May 8, 2025Updated last year