Minimal hackable GRPO implementation
☆338Jan 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:
- Exploring Applications of GRPO☆252Aug 25, 2025Updated 8 months ago
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,675Nov 21, 2025Updated 6 months ago
- ☆71Jul 28, 2024Updated last year
- ☆68May 23, 2025Updated 11 months ago
- Collection of LLM completions for reasoning-gym task datasets☆31Jul 4, 2025Updated 10 months 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.
- 🐭 A tiny single-file implementation of Group Relative Policy Optimization (GRPO) as introduced by the DeepSeekMath paper☆42Jun 28, 2025Updated 10 months ago
- minimal GRPO implementation from scratch☆103Mar 14, 2025Updated last year
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,426Apr 17, 2026Updated last month
- RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.☆80Feb 19, 2025Updated last year
- Muon fsdp 2☆58Aug 8, 2025Updated 9 months ago
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆143May 8, 2025Updated last year
- Building the cognitive-core to solve ARC-AGI-2☆27Feb 2, 2025Updated last year
- Simple RL training for reasoning☆3,859Dec 23, 2025Updated 4 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆60Oct 18, 2025Updated 7 months 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.
- Reinforcing General Reasoning without Verifiers☆100Jun 24, 2025Updated 10 months ago
- Our library for RL environments + evals☆4,125Updated this week
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,259Aug 27, 2025Updated 8 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Oct 9, 2024Updated last year
- Fully open reproduction of DeepSeek-R1☆26,020Apr 2, 2026Updated last month
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆613Oct 7, 2025Updated 7 months ago
- Minimal reproduction of DeepSeek R1-Zero☆13,104Feb 27, 2026Updated 2 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆654Jan 29, 2026Updated 3 months ago
- System 2 Reasoning Link Collection☆874Mar 16, 2025Updated last year
- 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.
- Dreamer on JAX☆16Jan 19, 2022Updated 4 years ago
- Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery☆17Apr 2, 2026Updated last month
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,668Apr 14, 2026Updated last month
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆94Mar 27, 2026Updated last month
- Solidity contracts for the decentralized Prime Network protocol☆26Jul 6, 2025Updated 10 months ago
- Verifiers for LLM Reinforcement Learning☆80Apr 15, 2025Updated last year
- Implements pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), to train and fine-tune the …☆57Mar 9, 2024Updated 2 years ago
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆17Apr 22, 2025Updated last year
- Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research☆15May 30, 2024Updated last year
- 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.
- ☆138Mar 20, 2025Updated last year
- Giving Up Control: Neurons as Reinforcement Learning Agents☆13May 6, 2024Updated 2 years ago
- Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning☆24Jun 25, 2025Updated 10 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆122Sep 22, 2024Updated last year
- TORCH_TRACE parser for PT2☆86May 11, 2026Updated last week
- Official repo for Learning to Reason for Long-Form Story Generation☆78Apr 19, 2025Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,859Mar 18, 2025Updated last year