lsdefine / simple_GRPOLinks
A very simple GRPO implement for reproducing r1-like LLM thinking.
☆1,535Updated last month
Alternatives and similar repositories for simple_GRPO
Users that are interested in simple_GRPO are comparing it to the libraries listed below
Sorting:
- Reproduce R1 Zero on Logic Puzzle☆2,431Updated 9 months ago
- A Survey of Reinforcement Learning for Large Reasoning Models☆2,237Updated 2 months ago
- Official Repo for Open-Reasoner-Zero☆2,087Updated 7 months ago
- O1 Replication Journey☆2,003Updated last year
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,702Updated 8 months ago
- Latest Advances on System-2 Reasoning☆1,304Updated 7 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,830Updated 11 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,414Updated last week
- ☆757Updated 3 weeks ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,470Updated last week
- ☆552Updated last year
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆2,619Updated this week
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆1,151Updated last month
- A series of technical report on Slow Thinking with LLM☆754Updated 5 months ago
- Simple RL training for reasoning☆3,826Updated 3 weeks ago
- minimal-cost for training 0.5B R1-Zero☆799Updated 8 months ago
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,381Updated this week
- llm & rl☆265Updated 2 months ago
- Scalable RL solution for advanced reasoning of language models☆1,794Updated 9 months ago
- 欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩🎓👨🎓☆914Updated last month
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆1,381Updated last month
- A fork to add multimodal model training to open-r1☆1,435Updated 11 months ago
- 这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。☆722Updated 10 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆688Updated 11 months ago
- ☆1,411Updated 4 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆784Updated 8 months ago
- ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Rei…☆1,285Updated 7 months ago
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆836Updated 8 months ago
- Awesome List for Agentic RL☆706Updated last month
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆717Updated 2 months ago