lsdefine / simple_GRPOLinks
A very simple GRPO implement for reproducing r1-like LLM thinking.
☆1,438Updated 3 months ago
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☆2,411Updated 7 months ago
- Latest Advances on System-2 Reasoning☆1,265Updated 5 months ago
- A Survey of Reinforcement Learning for Large Reasoning Models☆2,001Updated last week
- Official Repo for Open-Reasoner-Zero☆2,060Updated 5 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,626Updated 6 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,823Updated 9 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,029Updated last week
- O1 Replication Journey☆2,002Updated 10 months ago
- ☆749Updated 2 months ago
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆874Updated 3 months ago
- A series of technical report on Slow Thinking with LLM☆743Updated 3 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,390Updated this week
- minimal-cost for training 0.5B R1-Zero☆784Updated 6 months ago
- ☆548Updated 10 months ago
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆2,264Updated this week
- 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。👩🎓👨🎓☆895Updated this week
- Scalable RL solution for advanced reasoning of language models☆1,767Updated 7 months ago
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆2,977Updated this week
- A fork to add multimodal model training to open-r1☆1,416Updated 9 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆746Updated 6 months ago
- Simple RL training for reasoning☆3,784Updated 3 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆676Updated 9 months ago
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆828Updated 6 months ago
- llm & rl☆243Updated 3 weeks ago
- ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning☆1,241Updated 5 months ago
- ☆1,169Updated 2 months ago
- Large Reasoning Models☆806Updated 11 months ago
- ☆995Updated 4 months ago
- 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…☆1,154Updated 3 weeks ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆926Updated 8 months ago