100M tokens. Infinite compute. Lowest val loss wins.
☆528Jul 3, 2026Updated last month
Alternatives and similar repositories for slowrun
Users that are interested in slowrun are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NanoGPT (124M) in 90 seconds☆5,715Aug 9, 2026Updated 2 weeks ago
- Minimal and highly hackable implementation of Looped Transformers with GPT☆25Mar 8, 2026Updated 5 months ago
- Train the smallest LM you can that fits in 16MB. Best model wins!☆5,171May 4, 2026Updated 3 months ago
- CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.☆80Jul 30, 2026Updated 3 weeks ago
- Open-source framework for the research and development of foundation models.☆2,988Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 🧱 Modula software package☆338Aug 18, 2025Updated last year
- Muon is an optimizer for hidden layers in neural networks☆2,807May 24, 2026Updated 3 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆203Jan 19, 2026Updated 7 months ago
- MoE training for Me and You and maybe other people☆396Mar 15, 2026Updated 5 months ago
- A transformer that executes a one-instruction Turing-complete computer — two approaches: hand-coded weights (no training) and learned fro…☆41Mar 3, 2026Updated 5 months ago
- Dion optimizer algorithm☆539Updated this week
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆389Nov 15, 2025Updated 9 months ago
- ☆278Dec 2, 2024Updated last year
- Tiny evaluation of leading LLMs on competitive programming problems☆14Apr 10, 2026Updated 4 months ago
- 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.
- Code for "Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models".☆24Mar 16, 2026Updated 5 months ago
- Simple Transformer in Jax☆143Jun 22, 2024Updated 2 years ago
- Code for "What really matters in matrix-whitening optimizers?"☆25Oct 31, 2025Updated 9 months ago
- Our library for RL environments + evals☆4,569Updated this week
- Efficient optimizers☆339Updated this week
- EvaByte: Efficient Byte-level Language Models at Scale☆119Apr 22, 2025Updated last year
- Agentic RL Training at Scale☆1,991Updated this week
- [ICML 2026] NITP: Next Implicit Token Prediction for LLM Pre-training☆35May 26, 2026Updated 3 months ago
- a whirlwind tour to deep learning and deep learning systems☆82Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆145May 6, 2026Updated 3 months ago
- ☆23Mar 11, 2026Updated 5 months ago
- TEVO: evolve LM motifs cheaply, then validate them in downstream train.py loops.☆19Apr 18, 2026Updated 4 months ago
- Use Muon optimizer instead of AdamW.☆50Mar 2, 2026Updated 5 months ago
- Tile primitives for speedy kernels☆3,658Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,659Updated this week
- Aggressive decode optimizations for Qwen3-0.6B on RTX 5090☆60Feb 25, 2026Updated 6 months ago
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆360Aug 21, 2026Updated last week
- ☆18Sep 6, 2025Updated 11 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆433Aug 5, 2026Updated 3 weeks ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆68Jul 30, 2026Updated last month
- Fast Polar Decomposition for Muon☆175Jul 2, 2026Updated last month
- Storing the LongCoT-mini results for RLM(GPT-5.2)☆20Apr 26, 2026Updated 4 months ago
- supporting pytorch FSDP for optimizers☆84Dec 8, 2024Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆112Mar 7, 2025Updated last year
- Muon is Scalable for LLM Training☆1,541Aug 3, 2025Updated last year