Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
☆611Oct 7, 2025Updated 7 months ago
Alternatives and similar repositories for nano-aha-moment
Users that are interested in nano-aha-moment are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SafeArena is a benchmark for assessing the harmful capabilities of web agents☆22Apr 23, 2025Updated last year
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,844Apr 18, 2025Updated last year
- Simple repository for training small reasoning models☆50Feb 17, 2026Updated 3 months ago
- A basic pure pytorch implementation of flash attention☆16Oct 28, 2024Updated last year
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,182Aug 26, 2025Updated 8 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- rl from zero pretrain, can it be done? yes.☆293Sep 28, 2025Updated 7 months ago
- Focused on fast experimentation and simplicity☆80Dec 24, 2024Updated last year
- ☆17Apr 9, 2025Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Apr 17, 2024Updated 2 years ago
- Official Repo for Open-Reasoner-Zero☆2,091Jun 2, 2025Updated 11 months ago
- Our library for RL environments + evals☆4,106Updated this week
- simple grpo☆12May 28, 2025Updated 11 months ago
- Build your own visual reasoning model☆422Jan 13, 2026Updated 4 months ago
- A bibliography and survey of the papers surrounding o1☆1,214Nov 16, 2024Updated last year
- 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.
- Minimal reproduction of DeepSeek R1-Zero☆13,099Feb 27, 2026Updated 2 months ago
- Agentic RL Training at Scale☆1,359May 12, 2026Updated last week
- Synthetic Data Generation for Evaluation☆14Feb 21, 2025Updated last year
- ☆138Dec 9, 2025Updated 5 months ago
- Exploring Applications of GRPO☆252Aug 25, 2025Updated 8 months ago
- ☆15Apr 26, 2025Updated last year
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,253Aug 27, 2025Updated 8 months ago
- What would you do with 1000 H100s...☆1,173Jan 10, 2024Updated 2 years ago
- Simple RL training for reasoning☆3,856Dec 23, 2025Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,760Jul 18, 2025Updated 10 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆68Mar 5, 2026Updated 2 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆286Nov 24, 2025Updated 5 months ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,861Oct 27, 2025Updated 6 months ago
- Muon is Scalable for LLM Training☆1,475Aug 3, 2025Updated 9 months ago
- NanoGPT (124M) in 90 seconds☆5,233Updated this week
- Minimalistic large language model 3D-parallelism training☆2,690Apr 7, 2026Updated last month
- Efficient Triton Kernels for LLM Training☆6,350May 11, 2026Updated last week
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Dec 29, 2025Updated 4 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,337Updated this week
- Muon is an optimizer for hidden layers in neural networks☆2,567Jan 19, 2026Updated 4 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆345Nov 2, 2025Updated 6 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆124Aug 22, 2024Updated last year
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,418Apr 17, 2026Updated last month
- Code repository for the paper "The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Le…☆14Jan 16, 2025Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,507Updated this week