RL Swarm is a fully open-source framework developed by GensynAI for building reinforcement learning (RL) training swarms over the internet. This guide walks you through setting up an RL Swarm node and a web UI dashboard to monitor swarm activity.
- CPU: Minimum 16GB RAM (more RAM recommended for larger models or datasets).
OR
- GPU (Optional): Supported CUDA devices for enhanced performance:
- RTX 3090
- RTX 4090
- A100
- H100
I recommend GPUs with >=24GB vRAM.
- Note: You can run the node without a GPU using CPU-only mode.
1. Update System Packages
sudo apt-get update && sudo apt-get upgrade -y2. Install General Utilities and Tools
sudo apt install screen curl iptables build-essential git wget lz4 jq make gcc nano automake autoconf tmux htop nvme-cli libgbm1 pkg-config libssl-dev libleveldb-dev tar clang bsdmainutils ncdu unzip libleveldb-dev -y3. Install Python
sudo apt-get install python3 python3-pip python3-venv python3-dev -y4. Install Node
sudo apt-get update && curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs && curl -o- -L https://yarnpkg.com/install.sh | bash && echo 'export PATH="$HOME/.yarn/bin:$HOME/.config/yarn/global/node_modules/.bin:$PATH"' >> ~/.bashrc && source ~/.bashrc5. Install Ngrok
sudo snap install ngrok1- Create account in HuggingFace
2- Create an Access Token with Write permissions here and save it
git clone https://github.com/gensyn-ai/rl-swarm/ && cd rl-swarmOpen a screen to run it in background
screen -S gensynInstall swarm
python3 -m venv .venv && source .venv/bin/activate && ./run_rl_swarm.shPress Y
1- You have to receive Waiting for userData.json to be created... in logs
2- Open login page in browser
- Local PC:
http://localhost:3000/ - VPS users: Do not receive OTP code in emails by logging in 3000 port on browser. You have to forward port by entering a command in their local pc powershell command prompt. (Step 3 of this section)
3-
- In windows start menu, Search Powershell and open its terminal in your local PC
- Enter the command below and replace your vps ip with
Server_IPand your vps port(.eg 22) withSSH_PORT
ssh -L 3000:localhost:3000 root@Server_IP -p SSH_PORT
⚠️ Make sure you enter the command in your own local Windows Powershell cmd and NOT your VPS terminal.- This prompts you to enter your VPS password, when you enter it, you connect and tunnel to your vps
- Now go to browser and open
http://localhost:3000/and login
4- Login with your preferred method
- After login, your terminal starts installation.
5- Optional: Push models to huggingface
- Enter your
HuggingFaceaccess token you've created when it prompted - This will need
2GBupload bandwidth for each model you train, you can pass it by enteringN
- Now your node started running, Find your name after word
Hello, like mine iswhistling hulking armadilloas in the image below (You can useCTRL+SHIFT+Fto search Hello in terminal)
- Minimize:
CTRL+A+D - Return:
screen -r swarm - Stop and Kill:
screen -XS swarm quit
You need to backup swarm.pem.
Connect your VPS using Mobaxterm client to be able to move files to your local system. Back up these files:**
/root/rl-swarm/swarm.pem
Search \\wsl.localhost in your Windows Explorer to see your Ubuntu directory. Your main directories are as follows:
- If installed via a username:
\\wsl.localhost\Ubuntu\home\<your_username> - If installed via root:
\\wsl.localhost\Ubuntu\root - Look for
rl-swarm/swarm.pem
1- Connect to your GPU server by entering this command in Windows PowerShell terminal
sftp -P PORT ubuntu@xxxx.hyperbolic.xyz
- Replace
ubuntu@xxxx.hyperbolic.xyzwith your given GPU hostname - Replace
PORTwith your server port (in your server ssh connection command) ubuntuis the user of my hyperbolic gpu, it can be anything else or it'srootif you test it out forvps
Once connected, you’ll see the SFTP prompt:
sftp>
2- Navigate to the Directory Containing the Files
- After connecting, you’ll start in your home directory on the server. Use the
cdcommand to move to the directory of your files:
cd /home/ubuntu/rl-swarm
3- Download Files
- Use the
getcommand to download the files to yourlocal system. They’ll save to your current local directory unless you specify otherwise:
get swarm.pem
- Downloaded file is in the main directory of your
PowershellorWSLwhere you entered the sFTP command.- If entered sftp command in
Porwershell, theswarm.pemfile might be inC:\Users\<pc-username>.
- If entered sftp command in
- You can now type
exitto close connection. The files are in the main directory of yourPowershellorWSLwhere you entered the first SFTP command.
If you need to upload files from your local machine to the server.
WSL&VPS: Drag & Drop option.
GPU servers (.eg, Hyperbolic):
1- Connect to your GPU server using sFTP
2- Upload Files Using the put Command:
In SFTP, the put command uploads files from your local machine to the server.
put swarm.pem /home/ubuntu/rl-swarm/swarm.pem- To install the node on Hyperbolic check this Guide: Rent & Connect to GPU
- Add this flag:
-L 3000:localhost:3000in front of your Hyperbolic'sSSH-command, this will allow you to access to login page via local system.
- 1- Register in Vast.ai
- 2- Create ssh key in your local system (If you don't have already) with this Guide: step 1-5
- 3- Paste SSH public key to
Setting > SSH Keyshere - 4- Select Pytorch(Vast) template here
- 5- Choose a supported GPU (I recommend >=24GB Per-GPU vRAM)
- 6- Increase
Disk Spaceslidebar to200GB - 7- Top-up with credits and rent it.
- 8- Go to instances, refresh the page, click on
keybutton - 9- Create an ssh key,
- 10- Copy SSH Command, and Replace
-L 3000:localhost:3000in front of the command. - 11- Enter the command in
Windows Powershelland run it
- Top 100 round-participants: https://dashboard.gensyn.ai/
Search you Node ID here with /check here: https://t.me/gensyntrackbot
Node-IDis near your Node name
⚠️ If receivingEVM Wallet: 0x0000000000000000000000000000000000000000, youronchain-participationis not being tracked and you have to Install withNew Emailand Delete oldswarm.pem
1- Modify: package.json
cd rl-swarm
nano modal-login/package.json- Update:
"viem":to"2.25.0"
2- Upgrade
cd rl-swarm
cd modal-login
yarn install
yarn upgrade && yarn add next@latest && yarn add viem@latest
cd ..Navigate:
cd rl-swarm
Edit:
nano hivemind_exp/configs/mac/grpo-qwen-2.5-0.5b-deepseek-r1.yaml
- Lower
max_stepsto5