A very simple GRPO implement for reproducing r1-like LLM thinking.
☆1,675Nov 21, 2025Updated 6 months ago
Alternatives and similar repositories for simple_GRPO
Users that are interested in simple_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:
- Reproduce R1 Zero on Logic Puzzle☆2,450Mar 20, 2025Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,523May 15, 2026Updated last week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,337May 16, 2026Updated last week
- Fully open reproduction of DeepSeek-R1☆26,020Apr 2, 2026Updated last month
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,950Apr 6, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Simple RL training for reasoning☆3,859Dec 23, 2025Updated 4 months ago
- Official Repo for Open-Reasoner-Zero☆2,091Jun 2, 2025Updated 11 months ago
- Minimal hackable GRPO implementation☆338Jan 31, 2025Updated last year
- minimal-cost for training 0.5B R1-Zero☆816May 14, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,104Feb 27, 2026Updated 2 months ago
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,850Apr 18, 2025Updated last year
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,810May 11, 2025Updated last year
- Train transformer language models with reinforcement learning.☆18,411Updated this week
- ☆766Dec 23, 2025Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆71,468Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆14,218Updated this week
- Witness the aha moment of VLM with less than $3.☆4,057May 19, 2025Updated last year
- O1 Replication Journey☆2,000Jan 14, 2025Updated last year
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,259Aug 27, 2025Updated 8 months ago
- Democratizing Reinforcement Learning for LLMs☆5,548Updated this week
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,668Apr 14, 2026Updated last month
- Explore the Multimodal “Aha Moment” on 2B Model☆623Mar 18, 2025Updated last year
- A fork to add multimodal model training to open-r1☆1,548Feb 8, 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.
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆4,753Nov 13, 2025Updated 6 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,203Updated this week
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆92Feb 14, 2025Updated last year
- A series of technical report on Slow Thinking with LLM☆765Aug 13, 2025Updated 9 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,842Jan 17, 2025Updated last year
- Solve Visual Understanding with Reinforced VLMs☆5,959Mar 12, 2026Updated 2 months ago
- s1: Simple test-time scaling☆6,655Jun 25, 2025Updated 10 months ago
- [NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.☆535Sep 27, 2025Updated 7 months ago
- A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.☆6,901Dec 17, 2025Updated 5 months ago
- 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.
- ☆219Feb 20, 2025Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,859Mar 18, 2025Updated last year
- The open source code of ALMTokenizer2: Towards Low bit-rate and Semantic-rich Audio Tokenizer with Flow-based Scalar Diffusion Transforme…☆45Sep 5, 2025Updated 8 months ago
- The demo page for ALMTokenizer☆59Apr 14, 2025Updated last year
- ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Rei…☆1,385May 16, 2025Updated last year
- ☆814Jun 9, 2025Updated 11 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,165Updated this week