Deploying and Using Qwen2.5-VL-32B-Instruct on Hyperstack: A Quick Guide

What is Qwen2.5-VL-32B-Instruct?

​Qwen2.5-VL-32B-Instruct is an advanced 32-billion-parameter vision-language model from Alibaba's Qwen series. This model is designed to understand and generate both visual and textual content. It excels in recognising objects, analysing complex visuals like charts and layouts, and processing lengthy videos by identifying pertinent segments. The model can also accurately localise objects within images, offering structured outputs suitable for applications in finance and commerce.

The new qwen model has made more enhancements through reinforcement learning to improve its mathematical and problem-solving abilities, aligning its responses more closely with human preferences

Features of Qwen2.5-VL-32B-Instruct

The key features of Alibaba's latest Qwen2.5-VL-32B-Instruct model include:

• Advanced Visual Understanding: Recognises common objects like flowers, birds, fish and insects while excelling at analysing texts, charts, icons, graphics and layouts within images.
• Agentic Capabilities: Functions as a visual agent capable of reasoning and dynamically using tools, including interactions with computers and mobile devices.
• Long-Video Comprehension: Understands videos exceeding one hour in length and can accurately capture events by pinpointing relevant segments.
• Precise Visual Localisation: Identifies objects in images with high accuracy, providing bounding boxes or points and generating stable JSON outputs for coordinates and attributes.
• Structured Data Extraction: Processes scans of invoices, forms, tables and other structured data, enabling applications in finance, commerce and related fields.

Steps to Deploy Qwen2.5-VL-32B-Instruct on Hyperstack

Now, let's walk through the step-by-step process of deploying Qwen2.5-VL-32B-Instruct 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 "2xA100-80G-PCIe" flavour. 1xA100-80G-PCIe is compatible but requires modification of the MAX_MODEL_LEN on lines 13 and 14 of the cloud-init script (see the 'Configure Additional Settings' step for the script)

Choose the Operating System

1. Select the "Ubuntu Server 22.04 LTS R550 CUDA 12.4 with Docker". 

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 connect and manage your VM securely.

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! 

Please note: this cloud-init script will only enable the API  once for demo-ing purposes. For production environments, consider using containerization (e.g. Docker), secure connections, secret management, and monitoring for your API.

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 5-10 minutes. During this time, the script performs several crucial tasks:

1. Dependencies Installation: Installs all necessary libraries and tools required to run Qwen2.5-VL-32B-Instruct.
2. Model Download: Fetches the Qwen2.5-VL-32B-Instruct model files from the specified repository.

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 Qwen2.5-VL-32B-Instruct

To access and experiment with Qwen2.5-VL-32B-Instruct, 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 Qwen2.5-VL-32B-Instruct:

IMAGE_URL="https://www.hyperstack.cloud/hs-fs/hubfs/deploy-vm-11-ecd8c53003182041d3a2881d0010f6c6-1.png?width=3352&height=1852&name=deploy-vm-11-ecd8c53003182041d3a2881d0010f6c6-1.png"
MODEL_NAME="Qwen/Qwen2.5-VL-32B-Instruct"
curl -X POST http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "'$MODEL_NAME'",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Describe this image in two sentences"
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "'$IMAGE_URL'"
                        }
                    }
                ]
            }
        ]
    }

Troubleshooting Qwen2.5-VL-32B-Instruct

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.

Why Deploy Qwen2.5-VL-32B-Instruct 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 Qwen2.5-VL-32B-Instruct:

• Availability: Hyperstack provides access to the latest and most powerful GPUs such as the NVIDIA H100 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.

New to Hyperstack? Log in to Get Started with Our Ultimate Cloud GPU Platform Today!

FAQs

What is Qwen2.5-VL-32B-Instruct?

Qwen2.5-VL-32B-Instruct is a 32-billion-parameter vision-language model developed by Qwen, designed to understand and generate both visual and textual content.

What are the key features of Qwen2.5-VL-32B-Instruct?

The model excels in object recognition, analysis of complex visuals like charts and layouts, and processing lengthy videos by identifying pertinent segments. It can accurately localise objects within images and provides structured outputs suitable for applications in finance and commerce.

How does Qwen2.5-VL-32B-Instruct differ from previous models?

Compared to earlier models, Qwen2.5-VL-32B-Instruct has enhanced mathematical problem-solving abilities and improved performance in image parsing, content recognition and visual logic deduction tasks.

Is Qwen2.5-VL-32B-Instruct open-source?

Yes, Qwen2.5-VL-32B-Instruct is open-sourced under the Apache 2.0 license.

Where can I access Qwen2.5-VL-32B-Instruct?

The model is available on platforms like Hugging Face. You can access it through the Hugging Face repository here.