Train the smallest LM you can that fits in 16MB. Best model wins!
☆5,202Oct 22, 2026Updated 2 weeks ago
Alternatives and similar repositories for parameter-golf
Users that are interested in parameter-golf 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☆6,014Sep 28, 2026Updated last month
- 100M tokens. Infinite compute. Lowest val loss wins.☆579Oct 21, 2026Updated 2 weeks ago
- The best ChatGPT that $100 can buy.☆60,356Sep 7, 2026Updated 2 months ago
- AI agents running research on single-GPU nanochat training automatically☆99,453Mar 26, 2026Updated 7 months ago
- slime is an LLM training framework for RL Scaling.☆8,806Updated this week
- 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.
- Anthropic's original performance take-home, now open for you to try!☆4,215Jan 22, 2026Updated 9 months ago
- Archived — ML Intern is no longer maintained. Continue with HuggingChat.☆10,787Oct 22, 2026Updated 2 weeks ago
- 🚀 Efficient implementations for emerging model architectures☆6,026Updated this week
- Agentic RL Training at Scale☆2,224Updated this week
- Our library for RL environments + evals☆4,775Updated this week
- Post-training with Tinker☆4,240Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆96,513Updated this week
- Puffing up reinforcement learning☆6,584Oct 14, 2026Updated 3 weeks ago
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.☆79,150Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Open-source framework for the research and development of foundation models.☆4,079Updated this week
- gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI☆20,511Oct 29, 2026Updated last week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,162Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,560Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆64,523Nov 12, 2025Updated 11 months ago
- Renderer for the harmony response format to be used with gpt-oss☆4,539Apr 8, 2026Updated 6 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,503Updated this week
- Muon is an optimizer for hidden layers in neural networks☆2,928May 24, 2026Updated 5 months ago
- Lightweight coding agent that runs in your terminal☆133,565Updated 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.
- Tile primitives for speedy kernels☆3,795Sep 12, 2026Updated last month
- Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding ag…☆27,966Sep 15, 2026Updated last month
- Train transformer language models with reinforcement learning.☆19,684Updated this week
- Efficient Triton Kernels for LLM Training☆6,689Updated this week
- Fast and memory-efficient exact attention☆25,256Updated this week
- A PyTorch native platform for training generative AI models☆5,883Updated this week
- Development repository for the Triton language and compiler☆20,533Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,294Jul 9, 2026Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆1,189Oct 30, 2026Updated last 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.
- LLM training in simple, raw C/CUDA☆31,403Jun 26, 2025Updated last year
- ☆3,568Mar 17, 2026Updated 7 months ago
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,619Updated this week
- DSPy: The framework for programming—not prompting—language models☆38,967Updated this week
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models☆4,814Jan 14, 2026Updated 9 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,278Updated this week
- Nano vLLM☆16,338Apr 26, 2026Updated 6 months ago