Deploying and Using Qwen2-72B on Hyperstack: A Quick Start Guide

Qwen2-72B, built on the advanced Transformer architecture with features like SwiGLU activation and group query attention ensures optimal performance for various AI applications. With an improved tokenizer supporting multiple languages and code, this model is designed to handle diverse AI and ML tasks. Qwen2-72B outperformed LLama-3-70B instruct on multiple benchmarks, see below:

Click Here to Find the Image Source

Continue reading our quick start guide for a step-by-step approach to deploying and using Qwen2-72B on Hyperstack so you can maximise its potential for your AI projects.

Why Deploy on Hyperstack?

Hyperstack is a cloud platform designed to accelerate AI and machine learning workloads. Here's why it's an excellent choice for deploying Qwen2-72B:

• Availability: Hyperstack provides access to the latest and most powerful GPUs such as the NVIDIA A100 and the NVIDIA H100 SXM on-demand, specifically designed to handle large language models. 
• Ease of Deployment: With pre-configured environments and one-click deployments, setting up complex AI models becomes significantly simpler on our platform. 
• Scalability: You can easily scale your resources up or down based on your computational needs.
• Cost-Effectiveness: You pay only for the resources you use with our cost-effective cloud GPU pricing. 
• Integration Capabilities: Hyperstack provides easy integration with popular AI frameworks and tools.

Deployment Process

Now, let's walk through the step-by-step process of deploying Qwen2-72B on Hyperstack.

Step 1: Accessing Hyperstack

1. Go to the Hyperstack website and log in to your account.
2. If you're new to Hyperstack, you'll need to create an account and set up your billing information. Check our documentation to get started with Hyperstack.
3. Once logged in, you'll be greeted by the Hyperstack dashboard, which provides an overview of your resources and deployments.

Step 2: Deploying a New Virtual Machine

Initiate Deployment

1. Look for the "Deploy New Virtual Machine" button on the dashboard.
2. Click it to start the deployment process.

Select Hardware Configuration

1. In the hardware options, choose the "4xA100-80G-PCIe" flavour.
2. This configuration provides 4 NVIDIA A100 GPUs with 80GB memory each, connected via PCIe, offering exceptional performance for running Llama 3.1-70B.
   
3. Due to the increased context length, this model requires more GPU than usually. If you don't require this context length, you can consider  using a 2xA100-80G-PCIe and then reducing the max model length by setting --max_model_length 4096 at the end of the Docker run command.

Choose the Operating System

1. Select the "Server 22.04 LTS R535 CUDA 12.2".
2. This image comes pre-installed with Ubuntu 22.04 LTS and NVIDIA drivers (R535) along with CUDA 12.2, providing an optimised environment for AI workloads.

Select a keypair

1. Select one of the keypairs in your account. Don't have a keypair yet? See our Getting Started tutorial for creating one.

Network Configuration

1. Ensure you assign a Public IP to your Virtual machine.
2. This allows you to access your VM from the internet, which is crucial for remote management and API access.

Enable SSH Access

1. Make sure to enable an SSH connection.
2. You'll need this to securely connect and manage your VM.

Configure Additional Settings

1. Look for an "Additional Settings" or "Advanced Options" section.
2. Here, you'll find a field for cloud-init scripts. This is where you'll paste the initialisation script. Click here to get the cloud-init script! 
3. Ensure the script is in bash syntax. This script will automate the setup of your Qwen2-72B environment.

Review and Deploy

1. Double-check all your settings.
2. Click the "Deploy" button to launch your virtual machine.

Step 3: Initialisation and Setup

After deploying your VM, the cloud-init script will begin its work. This process typically takes about 7 minutes. During this time, the script performs several crucial tasks:

1. Dependencies Installation: Installs all necessary libraries and tools required to run Qwen2-72B.
2. Model Download: Fetches the Qwen2-72B model files from the specified repository.
3. API Setup: Configures the vLLM engine and sets up an OpenAI-compatible API endpoint on port 8000.

While waiting, you can prepare your local environment for SSH access and familiarise yourself with the Hyperstack dashboard.

Step 4: Accessing Your VM

Once the initialisation is complete, you can access your VM:

Locate SSH Details

1. In the Hyperstack dashboard, find your VM's details.
2. Look for the public IP address, which you will need to connect to your VM with SSH.

Connect via SSH

1. Open a terminal on your local machine.
2. Use the command ssh -i [path_to_ssh_key] [os_username]@[vm_ip_address] (e.g: ssh -i /users/username/downloads/keypair_hyperstack ubuntu@0.0.0.0.0)
3. Replace username and ip_address with the details provided by Hyperstack.

Interacting with Qwen2-72B

To access and experiment with Meta's latest model, SSH into your machine after completing the setup. If you are having trouble connecting with SSH, watch our recent platform tour video (at 4:08) for a demo. Once connected, use this API call on your machine to start using the Qwen2-72B. 

MODEL_NAME="Qwen/Qwen2-72B-Instruct"
curl -X POST http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "'$MODEL_NAME'",
        "messages": [
            {
                "role": "user",
                "content": "Hello, how are you?"
            }
        ]
    }'

If the API is not working after ~10 minutes, please refer to our 'Troubleshooting Qwen2-72B section below.

Troubleshooting Qwen2-72B

Step 5: Hibernating Your VM

When you're finished with your current workload, you can hibernate your VM to avoid incurring unnecessary costs:

1. In the Hyperstack dashboard, locate your Virtual machine.
2. Look for a "Hibernate" option.
3. Click to hibernate the VM, which will stop billing for compute resources while preserving your setup.

To continue your work without repeating the setup process:

1. Return to the Hyperstack dashboard and find your hibernated VM.
2. Select the "Resume" or "Start" option.
3. Wait a few moments for the VM to become active.
4. Reconnect via SSH using the same credentials as before.
   
   

Want to get started with Flux.1? Check out our tutorial below!

Deploying and Using Flux.1 on Hyperstack: A Quick Start Guide