Untitled https://paragraph.com/@0x32b87cfff2f4843b7b9ec60ae0b5d014f975331a undefined Sat, 12 Sep 2026 17:11:35 GMT https://validator.w3.org/feed/docs/rss2.html https://github.com/jpmonette/feed en All rights reserved <![CDATA[Gensyn testnet node guide]]> https://paragraph.com/@0x32b87cfff2f4843b7b9ec60ae0b5d014f975331a/gensyn-testnet-node-guide rzJG89GpVR1QyK8eEx69 Tue, 01 Apr 2025 09:15:30 GMT Detailed Steps for Running rl-swarm on Windows

1. Install WSL and Linux

Running rl-swarm on Windows is not very well tested and may require some debugging to set up properly. You first need to install WSL and Linux on your Windows machine.

  1. Open PowerShell or Command Prompt (run as administrator)

  2. Execute the following command to install WSL and Ubuntu distribution:

    wsl --install

  3. Restart your computer

  4. When starting WSL for the first time, you'll need to set up a Linux username and password

2. Install Necessary Dependencies in WSL

  1. Open the WSL terminal (through the Start menu or by typing wsl in Command Prompt)

  2. Update the package list:

    sudo apt update && sudo apt upgrade -y

  3. Install Python and other necessary tools:

    sudo apt install python3 python3-pip python3-venv git curl -y

3. Resolve the Node.js Version Issue

Since the Ubuntu system has Node.js 12.22.9 by default, which is outdated and incompatible with js-cookie@3.0.5 used by rl-swarm, you need to manually upgrade Node.js to v14+:

  1. Remove the old Node.js (recommended but optional):

    sudo apt remove nodejs npm
sudo apt autoremove

  2. Add the NodeSource repository (for Node.js 22.x LTS):

    curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -

  3. Install Node.js:

    sudo apt-get install -y nodejs

  4. Verify the installation:

    node -v  # Should show v22.x.x
npm -v

4. Clone the rl-swarm Project

In the WSL terminal, execute:

git clone https://github.com/gensyn-ai/rl-swarm.git
cd rl-swarm

5. Run the Installation Script

rl-swarm uses an interactive installation script that will guide you through the installation process.

In the project directory, execute:

./run_rl_swarm.sh

The installation script will:

  • Verify if your environment meets the requirements

  • Install necessary Python dependencies

  • Set up and configure rl-swarm

During the installation, when asked for confirmation, press Enter or input 'Y' to continue.

6. Configure and Start rl-swarm

After installation, rl-swarm will start a local web interface. By default, you need to manually navigate to http://localhost:3000/ (if you're running on a VM, you'll need to manually navigate to this URL).

7. Possible Issues and Solutions

If you're running the model on CPU and encounter a Python RuntimeError, or if your training progress seems to have stopped, you can try the following solutions:

  1. Set this experimental fix:

    export PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 && ./run_rl_swarm.sh

  2. Add the following training argument in your device configuration file: Edit ./hivemind_exp/configs/<directory_relevant_to_your_device>/grpo-qwen-2.5-0.5b-deepseek-r1.yaml Add parameter: max_grad_norm=0.5

  3. Use floating point 32 instead of bfloat16 to train your model. This can be changed in the device configuration file.

8. User Experience

rl-swarm is fully open and permissionless, meaning you can run it on a basic consumer laptop at home or on a powerful GPU in the cloud. After running a node, you can launch a new swarm or join an existing one.

rl-swarm uses Hivemind for distributed training, allowing models on different nodes to collaboratively learn and improve.

Notes

  • Windows support for rl-swarm is not as robust as Linux, and may require some debugging.

  • If you have multiple GPUs and want to run multiple nodes on one machine, you'll need to manually adjust the configuration.

  • Different training speeds between machines are normal.

]]> 0x32b87cfff2f4843b7b9ec60ae0b5d014f975331a@newsletter.paragraph.com (Untitled) <![CDATA[Gensyn 测试网节点WINDOWS教程]]> https://paragraph.com/@0x32b87cfff2f4843b7b9ec60ae0b5d014f975331a/gensyn-windows AlHu2VOo5TnWIK7LKdSb Tue, 01 Apr 2025 09:10:41 GMT 在Windows上运行rl-swarm的详细步骤

1. 安装WSL和Linux

在Windows上运行rl-swarm并不是非常完善，可能需要一些调试才能正确设置。您需要先在Windows机器上安装WSL和Linux。

  1. 打开PowerShell或命令提示符（以管理员身份运行）

  2. 执行以下命令安装WSL和Ubuntu发行版：

    wsl --install

  3. 重启计算机

  4. 首次启动WSL时，您需要设置Linux用户名和密码

2. 在WSL中安装必要的依赖项

  1. 打开WSL终端（可以通过开始菜单或在命令提示符中输入wsl）

  2. 更新软件包列表：

    sudo apt update && sudo apt upgrade -y

  3. 安装Python和其他必要的工具：

    sudo apt install python3 python3-pip python3-venv git curl -y

3. 解决Node.js版本问题

由于Ubuntu系统默认安装的Node.js 12.22.9版本过旧，不兼容rl-swarm需要的js-cookie@3.0.5，您需要手动升级Node.js到v14+版本：

  1. 移除旧版Node.js（推荐但可选）：

    sudo apt remove nodejs npm
sudo apt autoremove

  2. 添加NodeSource仓库（安装Node.js 22.x LTS版本）：

    curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -

  3. 安装Node.js：

    sudo apt-get install -y nodejs

  4. 验证安装：

    node -v  # 应显示v22.x.x
npm -v

4. 克隆rl-swarm项目

在WSL终端中执行：

git clone https://github.com/gensyn-ai/rl-swarm.git
cd rl-swarm

5. 运行安装脚本

rl-swarm使用一个交互式的安装脚本，该脚本会引导您完成安装过程。

在项目目录中执行：

./run_rl_swarm.sh

安装脚本会执行以下操作：

  • 验证您的环境是否满足要求

  • 安装必要的Python依赖项

  • 设置和配置rl-swarm

在安装过程中，当询问您是否确认时，按下Enter键或输入'Y'继续。

6. 配置和启动rl-swarm

安装完成后，rl-swarm会在本地启动一个Web界面，默认情况下您需要手动导航到http://localhost:3000/（如果您在虚拟机上运行，则需要手动导航到此URL）。

7. 可能遇到的问题和解决方案

如果您在CPU上运行模型并遇到Python RuntimeError，或者训练进度似乎停止了，可以尝试以下解决方法：

  1. 设置实验性修复：

    export PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 && ./run_rl_swarm.sh

  2. 在设备配置文件中添加训练参数： 编辑./hivemind_exp/configs/<与您设备相关的目录>/grpo-qwen-2.5-0.5b-deepseek-r1.yaml 添加参数：max_grad_norm=0.5

  3. 使用floating point 32而不是bfloat16来训练模型。这可以在设备配置文件中更改。

8. 使用体验

rl-swarm是一个完全开放和无需许可的系统，这意味着您可以在家中的基本消费级笔记本电脑上或云中的强大GPU上运行它。 运行节点后，您可以启动新的群组或加入现有的群组。

rl-swarm使用Hivemind进行分布式训练，让不同节点上的模型可以协作学习和改进。

注意事项

  • rl-swarm的Windows支持不如Linux完善，可能需要进行一些调试。

  • 如果您有多个GPU，想要在一台机器上运行多个节点，需要手动调整配置。

  • 不同机器之间的训练速度可能不同，这是正常的。

]]> 0x32b87cfff2f4843b7b9ec60ae0b5d014f975331a@newsletter.paragraph.com (Untitled)