Minimal hackable GRPO implementation
☆344Jan 31, 2025Updated last year
Alternatives and similar repositories for tiny-grpo
Users that are interested in tiny-grpo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,699Nov 21, 2025Updated 8 months ago
- Exploring Applications of GRPO☆252Aug 25, 2025Updated 10 months ago
- 🐭 A tiny single-file implementation of Group Relative Policy Optimization (GRPO) as introduced by the DeepSeekMath paper☆43Jun 28, 2025Updated last year
- Collection of LLM completions for reasoning-gym task datasets☆31Jul 4, 2025Updated last year
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,463Apr 17, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- minimal GRPO implementation from scratch☆104Mar 14, 2025Updated last year
- ☆69May 23, 2025Updated last year
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆143May 8, 2025Updated last year
- Code for PuzzleJAX, a benchmark for reasoning and learning, that reimplements PuzzleScript, a concise and expressive DSL and game engine …☆29Jun 30, 2026Updated 3 weeks ago
- Simple RL training for reasoning☆3,868Dec 23, 2025Updated 7 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆60Oct 18, 2025Updated 9 months ago
- ☆24Mar 23, 2026Updated 3 months ago
- ☆24Jan 22, 2026Updated 6 months ago
- Our library for RL environments + evals☆4,392Updated this week
- 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.
- autonomous nanogpt optimizer speedrun☆109May 14, 2026Updated 2 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,268Aug 27, 2025Updated 10 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,834Jul 14, 2026Updated last week
- Entropy Based Sampling and Parallel CoT Decoding☆17Oct 9, 2024Updated last year
- Fully open reproduction of DeepSeek-R1☆26,412Apr 2, 2026Updated 3 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆625Oct 7, 2025Updated 9 months ago
- Minimal reproduction of DeepSeek R1-Zero☆13,198Feb 27, 2026Updated 4 months ago
- System 2 Reasoning Link Collection☆875Mar 16, 2025Updated last year
- Dreamer on JAX☆16Jan 19, 2022Updated 4 years ago
- 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.
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆667Jan 29, 2026Updated 5 months ago
- ☆47Oct 23, 2025Updated 8 months ago
- Building the cognitive-core to solve ARC-AGI-2☆28Feb 2, 2025Updated last year
- Solidity contracts for the decentralized Prime Network protocol☆26Jul 6, 2025Updated last year
- RL models to play Sokoban. The fastest recipe wins.☆31Jul 15, 2026Updated last week
- Reproduction of 'Analysing Mathematical Reasoning Abilities of Neural Models' Saxton et. al. 2019☆12Dec 8, 2022Updated 3 years ago
- NSA Triton Kernels written with GPT5 and Opus 4.1☆70Aug 12, 2025Updated 11 months ago
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆17Apr 22, 2025Updated last year
- ☆1,298May 20, 2026Updated 2 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.
- rl from zero pretrain, can it be done? yes.☆295Sep 28, 2025Updated 9 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆129Sep 22, 2024Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,865Mar 18, 2025Updated last year
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,753Apr 14, 2026Updated 3 months ago
- Muon fsdp 2☆64Aug 8, 2025Updated 11 months ago
- Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research☆15May 30, 2024Updated 2 years ago
- Official repo for Learning to Reason for Long-Form Story Generation☆78Apr 19, 2025Updated last year