lsdefine / simple_GRPO
A very simple GRPO implement for reproducing r1-like LLM thinking.
☆1,029Updated last month
Alternatives and similar repositories for simple_GRPO:
Users that are interested in simple_GRPO are comparing it to the libraries listed below
- Latest Advances on System-2 Reasoning☆989Updated 2 weeks ago
- Reproduce R1 Zero on Logic Puzzle☆2,331Updated last month
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆2,315Updated this week
- Official Repo for Open-Reasoner-Zero☆1,912Updated last month
- O1 Replication Journey☆1,987Updated 3 months ago
- Awesome RL Reasoning Recipes ("Triple R")☆520Updated this week
- ☆526Updated 4 months ago
- ☆684Updated 3 weeks ago
- Distributed RL System for LLM Reasoning☆1,229Updated 2 weeks ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,765Updated 3 months ago
- A fork to add multimodal model training to open-r1☆1,252Updated 3 months ago
- A series of technical report on Slow Thinking with LLM☆659Updated 3 weeks ago
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆458Updated this week
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆748Updated last week
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,219Updated last month
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆619Updated 3 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。☆386Updated 2 months ago
- Awesome RL-based LLM Reasoning☆480Updated last week
- minimal-cost for training 0.5B R1-Zero☆716Updated 2 weeks ago
- Large Reasoning Models☆804Updated 5 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆1,772Updated this week
- Explore the Multimodal “Aha Moment” on 2B Model☆585Updated last month
- This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-bas…☆740Updated this week
- DeepSeek 系列工作解读、扩展和复现。☆641Updated last month
- 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。👩🎓👨🎓☆718Updated 3 weeks ago
- Scalable RL solution for advanced reasoning of language models☆1,537Updated last month
- R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning☆509Updated 3 weeks ago
- MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning☆592Updated last week
- Simple RL training for reasoning☆3,540Updated last month
- ☆683Updated last week