lsdefine / simple_GRPOLinks
A very simple GRPO implement for reproducing r1-like LLM thinking.
☆1,076Updated 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☆2,347Updated 2 months ago
- Latest Advances on System-2 Reasoning☆1,041Updated last month
- Official Repo for Open-Reasoner-Zero☆1,939Updated last month
- ☆538Updated 5 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆2,515Updated this week
- ☆706Updated this week
- Awesome RL Reasoning Recipes ("Triple R")☆580Updated this week
- Distributed RL System for LLM Reasoning☆1,284Updated this week
- A series of technical report on Slow Thinking with LLM☆679Updated this week
- O1 Replication Journey☆1,990Updated 4 months ago
- A fork to add multimodal model training to open-r1☆1,281Updated 3 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,776Updated 4 months ago
- minimal-cost for training 0.5B R1-Zero☆730Updated 2 weeks ago
- DeepSeek 系列工作解读、扩展和复现。☆652Updated 2 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆630Updated 4 months ago
- Awesome RL-based LLM Reasoning☆506Updated 3 weeks ago
- Train a 1B LLM with 1T tokens from scratch by personal☆663Updated last month
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,284Updated 3 weeks ago
- Scalable RL solution for advanced reasoning of language models☆1,587Updated 2 months ago
- Large Reasoning Models☆804Updated 5 months ago
- Simple RL training for reasoning☆3,601Updated last month
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆518Updated this week
- 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。☆408Updated 3 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆1,908Updated this week
- Latest Advances on Long Chain-of-Thought Reasoning☆343Updated this week
- Understanding R1-Zero-Like Training: A Critical Perspective☆956Updated last week
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆760Updated 2 weeks ago
- ☆731Updated 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。👩🎓👨🎓☆756Updated 2 weeks ago
- Explore the Multimodal “Aha Moment” on 2B Model☆589Updated 2 months ago