lsdefine / simple_GRPO
A very simple GRPO implement for reproducing r1-like LLM thinking.
☆964Updated 2 weeks ago
Alternatives and similar repositories for simple_GRPO:
Users that are interested in simple_GRPO are comparing it to the libraries listed below
- Reproduce R1 Zero on Logic Puzzle☆2,303Updated last month
- Latest Advances on System-2 Reasoning☆940Updated this week
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆2,069Updated this week
- ☆516Updated 3 months ago
- Awesome RL Reasoning Recipes ("Triple R")☆375Updated last week
- Official Repo for Open-Reasoner-Zero☆1,872Updated last week
- ☆659Updated this week
- minimal-cost for training 0.5B R1-Zero☆699Updated 3 weeks ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,756Updated 3 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。👩🎓👨🎓☆692Updated this week
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆613Updated 3 months ago
- A series of technical report on Slow Thinking with LLM☆630Updated last week
- O1 Replication Journey☆1,985Updated 3 months ago
- A fork to add multimodal model training to open-r1☆1,212Updated 2 months ago
- Awesome RL-based LLM Reasoning☆438Updated last week
- ☆381Updated this week
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆716Updated this week
- Distributed RL System for LLM Reasoning☆1,124Updated 2 weeks ago
- Large Reasoning Models☆802Updated 4 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,141Updated last week
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆1,382Updated this week
- DeepSeek 系列工作解读、扩展和复现。☆625Updated 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。☆359Updated 2 months ago
- Explore the Multimodal “Aha Moment” on 2B Model☆572Updated last month
- This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-bas…☆651Updated this week
- ☆630Updated 3 weeks ago
- Train a 1B LLM with 1T tokens from scratch by personal☆608Updated last month
- MM-EUREKA: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning☆556Updated this week
- Simple RL training for reasoning☆3,472Updated last week
- Scalable RL solution for advanced reasoning of language models☆1,488Updated last month