Effortless Deployment of DeepSeek-R1 on Hyperstack

Launching DeepSeek-R1 Image on Hyperstack

Great news! Hyperstack now offers a DeepSeek-R1 image (Beta) that lets you instantly deploy OpenWebUI with DeepSeek running on your machine. Simply select the 'DeepSeek' image from the list in the UI and your environment will be set up automatically—no manual configuration required.

IMPORTANT: Hyperstack's AI images are currently in Beta, and you may experience bugs or performance issues as we continue to refine them.

What is DeepSeek-R1?

DeepSeek-R1 is a 671B parameter Mixture-of-Experts (MoE) open-source language model with 37B activated parameters per token and a 128K context length, designed for high performance, cost efficiency, and scalability. It excels in logical inference, mathematical reasoning, and structured problem-solving, leveraging reinforcement learning to enhance reasoning capabilities and generate coherent responses. DeepSeek-R1 integrates Multi-head Latent Attention (MLA) with DeepSeekMoE to optimise inference speed and training efficiency. It also introduces an auxiliary-loss-free load-balancing strategy and supports Multi-Token Prediction (MTP) for improved text generation accuracy. Released under the MIT license, DeepSeek-R1 is fully open-source, allowing free use, modification and redistribution. 

How to Use DeepSeek-R1 Image on Hyperstack?

Follow these steps to set up and run the DeepSeek-R1 image on Hyperstack:

Step 1: Select Your GPU Configuration

Choose a suitable GPU configuration from the following options for your VM. The DeepSeek-R1 image has been successfully tested on the following GPU flavours. To ensure a smooth deployment, it is recommended to choose one of these flavours as selecting a different option may lead to deployment failure.

• 8x NVIDIA H100 PCIe
• 8x NVIDIA H100 NVLink
• 8x NVIDIA H100 SXM5

Step 2: Choose the DeepSeek Image

• Go to the "Select OS Image" section.
• From the dropdown menu, select 'DeepSeek R1 (int4) with OpenWebUI' as your image.

Interacting with DeepSeek-R1

1. Open your VM's firewall settings.

2. Allow port 3000 for your IP address (or leave it open to all IPs, though this is less secure and not recommended). For instructions, see here.

3. Visit http://[public-ip]:3000 in your browser. For example: http://198.145.126.7:3000

4. You can set up an admin account for OpenWebUI and save your username and password for future logins. See the attached screenshot.

And voila, you can start talking to your self-hosted DeepSeek R1! See an example below.

Optional: Increasing Context Size for DeepSeek-R1

The DeepSeek-R1 image comes with a default context size of 12,888 tokens. To modify it, follow these steps:

1. Click on your username at the bottom left and then on 'Admin Panel'.

2. Click on the "Settings" tab at the top.

3. Click on 'Models' in the left sidebar. This will take you to an overview of all the models available on your machine.

4. Click on the Pencil icon to the right of 'DeepSeek-r1-671B'.

5. Click on 'Advanced params' to find the context length.

You can now customise the Context Length by entering a value that meets your requirements.

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 DeepSeek-R1 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 DeepSeek-R1:

• 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.

FAQs

What is DeepSeek-R1?

DeepSeek-R1 is a 671B parameter open-source Mixture-of-Experts language model designed for high-performance logical reasoning and problem-solving.

What are the key features of DeepSeek-R1?

The key features of DeepSeek-R1 include:

• Advanced Reasoning Capabilities: DeepSeek-R1 excels in logical inference, mathematical reasoning, and real-time problem-solving, outperforming other models in tasks requiring structured thinking. 
• Reinforcement Learning Training: The model employs reinforcement learning techniques, allowing it to develop advanced reasoning skills and generate logically sound responses. 
• Open-Source: Released under the MIT license, DeepSeek-R1 is freely available for use, modification and redistribution.

How do I use the DeepSeek-R1 image on Hyperstack?

To use the DeepSeek image, create a new VM on Hyperstack, select ‘DeepSeek’ from the OS Image dropdown. Once deployed, access OpenWebUI at http://[public-ip]:3000 to interact with DeepSeek-R1.

Which GPUs are recommended for running DeepSeek-R1?

Choose a suitable GPU configuration from the following options for your VM. The DeepSeek-R1 image has been successfully tested on the following GPU flavours. To ensure a smooth deployment, it is recommended to choose one of these flavours as selecting a different option may lead to deployment failure.

• 8x NVIDIA H100 PCIe
• 8x NVIDIA H100 NVLink
• 8x NVIDIA H100 SXM5