lsdefine / simple_GRPO
A very simple GRPO implement for reproducing r1-like LLM thinking.
☆800Updated last week
Alternatives and similar repositories for simple_GRPO:
Users that are interested in simple_GRPO are comparing it to the libraries listed below
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆1,764Updated this week
- Reproduce R1 Zero on Logic Puzzle☆2,236Updated last week
- ☆507Updated 2 months ago
- Official Repo for Open-Reasoner-Zero☆1,687Updated 3 weeks ago
- minimal-cost for training 0.5B R1-Zero☆673Updated this week
- Latest Advances on System-2 Reasoning☆862Updated this week
- A series of technical report on Slow Thinking with LLM☆595Updated last week
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,736Updated 2 months ago
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆659Updated this week
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆597Updated 2 months ago
- O1 Replication Journey☆1,980Updated 2 months ago
- A fork to add multimodal model training to open-r1☆1,139Updated 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。👩🎓👨🎓☆636Updated this week
- ☆556Updated last week
- Awesome RL-based LLM Reasoning☆352Updated this week
- Explore the Multimodal “Aha Moment” on 2B Model☆538Updated last week
- DeepSeek 系列工作解读、扩展和复现。☆614Updated this week
- This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-bas…☆522Updated this week
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆915Updated this week
- Large Reasoning Models☆800Updated 3 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆589Updated 3 weeks 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。☆321Updated last month
- ☆574Updated 2 weeks ago
- Scalable RL solution for advanced reasoning of language models☆1,445Updated last week
- MM-EUREKA: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning☆459Updated this week
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆357Updated 2 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆851Updated last month
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆1,265Updated this week
- Recipes to train reward model for RLHF.☆1,257Updated last month
- ☆216Updated this week