Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality
☆331Jan 5, 2026Updated 2 months ago
Alternatives and similar repositories for PhysicsLM4
Users that are interested in PhysicsLM4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Proces…☆85Jan 12, 2025Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆144Feb 25, 2026Updated 3 weeks ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆186Jul 23, 2025Updated 8 months ago
- ☆133Jun 6, 2025Updated 9 months ago
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆79May 2, 2025Updated 10 months ago
- 🔥 A minimal training framework for scaling FLA models☆358Nov 15, 2025Updated 4 months ago
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆29Aug 19, 2025Updated 7 months ago
- ☆164Mar 17, 2026Updated last week
- ☆33Feb 11, 2025Updated last year
- Muon is Scalable for LLM Training☆1,446Aug 3, 2025Updated 7 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,630Updated this week
- ☆125Feb 4, 2026Updated last month
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆92Oct 30, 2024Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆48Oct 31, 2023Updated 2 years ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆516Mar 13, 2026Updated last week
- Open-source framework for the research and development of foundation models.☆803Updated this week
- [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆17Feb 9, 2026Updated last month
- Stick-breaking attention☆63Jul 1, 2025Updated 8 months ago
- Here we will test various linear attention designs.☆62Apr 25, 2024Updated last year
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆897Dec 20, 2025Updated 3 months ago
- ☆63Jun 12, 2025Updated 9 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆374Dec 12, 2024Updated last year
- Code for ICML 25 paper "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆50Jun 30, 2025Updated 8 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Dec 29, 2025Updated 2 months ago
- H-Net: Hierarchical Network with Dynamic Chunking☆826Nov 20, 2025Updated 4 months ago
- Supporting code for the blog post on modular manifolds.☆120Sep 26, 2025Updated 5 months ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆24May 20, 2025Updated 10 months ago
- Socratic-Zero is a fully autonomous framework that generates high-quality training data for mathematical reasoning☆36Oct 26, 2025Updated 4 months ago
- The official github repo for "Diffusion Language Models are Super Data Learners".☆225Nov 6, 2025Updated 4 months ago
- ☆110Feb 25, 2025Updated last year
- Code release for "Understanding Bias in Large-Scale Visual Datasets"☆23Dec 4, 2024Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Jul 17, 2025Updated 8 months ago
- ☆99Aug 8, 2025Updated 7 months ago
- ☆17Mar 23, 2025Updated last year
- Code release for paper "Test-Time Training Done Right"☆410Jan 5, 2026Updated 2 months ago
- Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics☆72Jan 13, 2026Updated 2 months ago
- AllenAI's post-training codebase☆3,643Updated this week
- Simple & Scalable Pretraining for Neural Architecture Research☆309Dec 6, 2025Updated 3 months ago
- Toolathlon-Gym for testing AI agents real-world tool-use capabilities across diverse MCP servers.☆87Updated this week