The simplest, fastest repository for training/finetuning medium-sized GPTs.
☆201Jan 19, 2026Updated 6 months ago
Alternatives and similar repositories for nanoGPT-mup
Users that are interested in nanoGPT-mup are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Sep 6, 2025Updated 11 months ago
- ☆19Nov 4, 2025Updated 9 months ago
- maximal update parametrization (µP)☆1,751Jul 17, 2024Updated 2 years ago
- ☆21Jun 12, 2025Updated last year
- ☆124May 28, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Dion optimizer algorithm☆531Updated this week
- Simple & Scalable Pretraining for Neural Architecture Research☆343Mar 31, 2026Updated 4 months ago
- ☆13Jun 3, 2024Updated 2 years ago
- ☆70Apr 8, 2026Updated 4 months ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆88Jul 28, 2024Updated 2 years ago
- 🧱 Modula software package☆337Aug 18, 2025Updated last year
- An implementation of the Llama architecture, to instruct and delight☆21May 31, 2025Updated last year
- supporting pytorch FSDP for optimizers☆84Dec 8, 2024Updated last year
- Fast Polar Decomposition for Muon☆173Jul 2, 2026Updated last month
- 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.
- NanoGPT (124M) in 90 seconds☆5,678Aug 9, 2026Updated last week
- Training hybrid models for dummies.☆31Nov 1, 2025Updated 9 months ago
- A library for unit scaling in PyTorch☆136Jul 11, 2025Updated last year
- ☆277Dec 2, 2024Updated last year
- ☆14Mar 2, 2025Updated last year
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,282Aug 26, 2025Updated 11 months ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆359Jul 29, 2024Updated 2 years ago
- Benchmarking Optimizers for LLM Pretraining☆60May 3, 2026Updated 3 months ago
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated 10 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.
- Spectral Sphere Optimizer☆132Mar 23, 2026Updated 4 months ago
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆83May 2, 2025Updated last year
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆357May 20, 2026Updated 2 months ago
- Open-source framework for the research and development of foundation models.☆1,265Updated this week
- ☆24Oct 15, 2024Updated last year
- Official code release for "SuperBPE: Space Travel for Language Models"☆98May 28, 2026Updated 2 months ago
- some mixture of experts architecture implementations☆28Mar 22, 2024Updated 2 years ago
- nanoGPT using Equinox☆15Mar 3, 2023Updated 3 years ago
- ☆221Aug 14, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆120Feb 25, 2025Updated last year
- Minimalistic large language model 3D-parallelism training☆2,785May 26, 2026Updated 2 months ago
- Stick-breaking attention☆63Jul 1, 2025Updated last year
- 100M tokens. Infinite compute. Lowest val loss wins.☆526Jul 3, 2026Updated last month
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Apr 17, 2024Updated 2 years ago
- 🚀 Efficient implementations for emerging model architectures☆5,569Updated this week