inclusionAI / AReaL
Distributed RL System for LLM Reasoning
☆1,164Updated this week
Alternatives and similar repositories for AReaL:
Users that are interested in AReaL are comparing it to the libraries listed below
- ☆698Updated this week
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆2,138Updated this week
- Reproduce R1 Zero on Logic Puzzle☆2,319Updated last month
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆986Updated 3 weeks ago
- Official Repo for Open-Reasoner-Zero☆1,887Updated 2 weeks ago
- ☆673Updated last week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,755Updated 3 weeks ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,758Updated 3 months ago
- DeepSeek 系列工作解读、扩展和复现。☆627Updated 3 weeks ago
- minimal-cost for training 0.5B R1-Zero☆706Updated this week
- Awesome RL Reasoning Recipes ("Triple R")☆410Updated this week
- Scalable RL solution for advanced reasoning of language models☆1,504Updated last month
- Train a 1B LLM with 1T tokens from scratch by personal☆613Updated last month
- ☆405Updated this week
- ☆518Updated 3 months ago
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆814Updated last week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆281Updated 3 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,171Updated 2 weeks ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆1,462Updated this week
- O1 Replication Journey☆1,985Updated 3 months ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,007Updated this week
- Community maintained hardware plugin for vLLM on Ascend☆515Updated this week
- Latest Advances on System-2 Reasoning☆956Updated this week
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,097Updated this week
- Muon is Scalable for LLM Training☆1,029Updated 3 weeks ago
- A fork to add multimodal model training to open-r1☆1,227Updated 2 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆342Updated 2 months ago
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆187Updated 2 months ago
- ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning☆714Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,068Updated last week