Install Now
How to install inclusionAI/AReaL. Official installation instructions. Project installation guide. Framework or library installation. Build installation instructions. How to setup and install from GitHub. Installation steps and setup instructions. Official docs and installation instructions GitHub.
inclusionAI/AReaL Installation Guide
How to install inclusionAI/AReaL. Official project installation instructions and setup guide.
⚡
Automated Install (Recommended)
Quick installation instructions for inclusionAI/AReaL. This is the fastest way to complete project installation and setup.
Install via curl
curl -fsSL https://hexmos.com/ipm-install | bash &&
ipm i inclusionAI/AReaLor
Install via npx
npx @hexmos/ipm i inclusionAI/AReaLPrerequisites
Python
languageVersion: >=3.8
CUDA
driverManual Installation Methods
Manual installation instructions. How to install from GitHub source.
Install from Source
git clone https://github.com/inclusionAI/AReaL
cd AReaL
pip install uv
uv sync --extra cudaPost Installation Steps
- Our training scripts automatically download the required dataset (openai/gsm8k) and model (Qwen/Qwen2-1.5B-Instruct).
- To run on a single node:
- python3 examples/math/gsm8k_rl.py --config examples/math/gsm8k_grpo.yaml scheduler.type=local
- To run on a Ray cluster with 2 nodes and 8 GPUs per node (remember to update paths in the YAML file to point to your shared storage):
- python3 examples/math/gsm8k_rl.py --config examples/math/gsm8k_grpo.yaml cluster.n_nodes=2 cluster.n_gpus_per_node=8 scheduler.type=ray