GitLab

Today, we are excited to announce that DeepSeek R1 distilled Llama and Qwen designs are available through Amazon Bedrock Marketplace and Amazon SageMaker JumpStart. With this launch, you can now release DeepSeek AI's first-generation frontier model, DeepSeek-R1, in addition to the distilled versions varying from 1.5 to 70 billion criteria to build, experiment, and properly scale your generative AI ideas on AWS.

In this post, we show how to get begun with DeepSeek-R1 on Amazon Bedrock Marketplace and SageMaker JumpStart. You can follow comparable actions to deploy the distilled variations of the designs as well.

Overview of DeepSeek-R1

DeepSeek-R1 is a big language design (LLM) developed by DeepSeek AI that utilizes reinforcement learning to enhance reasoning abilities through a multi-stage training process from a DeepSeek-V3-Base structure. A crucial differentiating function is its reinforcement learning (RL) action, which was utilized to refine the model's responses beyond the basic pre-training and fine-tuning procedure. By incorporating RL, DeepSeek-R1 can adjust better to user feedback and goals, ultimately boosting both importance and clarity. In addition, DeepSeek-R1 utilizes a chain-of-thought (CoT) technique, meaning it's equipped to break down complicated inquiries and factor through them in a detailed way. This guided reasoning process permits the design to produce more precise, transparent, and detailed responses. This model integrates RL-based fine-tuning with CoT capabilities, aiming to create structured reactions while focusing on interpretability and user interaction. With its comprehensive abilities DeepSeek-R1 has recorded the market's attention as a versatile text-generation design that can be incorporated into different workflows such as representatives, rational thinking and data interpretation tasks.

DeepSeek-R1 uses a Mix of Experts (MoE) architecture and is 671 billion parameters in size. The MoE architecture permits activation of 37 billion parameters, making it possible for effective inference by routing questions to the most relevant specialist "clusters." This technique permits the design to focus on various issue domains while maintaining total performance. DeepSeek-R1 requires at least 800 GB of HBM memory in FP8 format for inference. In this post, we will utilize an ml.p5e.48 xlarge circumstances to deploy the model. ml.p5e.48 xlarge comes with 8 Nvidia H200 GPUs offering 1128 GB of GPU memory.

DeepSeek-R1 distilled models bring the reasoning abilities of the main R1 model to more efficient architectures based on popular open models like Qwen (1.5 B, 7B, 14B, and 32B) and Llama (8B and 70B). Distillation refers to a procedure of training smaller, more efficient designs to simulate the habits and reasoning patterns of the bigger DeepSeek-R1 design, utilizing it as a teacher model.

You can deploy DeepSeek-R1 design either through SageMaker JumpStart or Bedrock Marketplace. Because DeepSeek-R1 is an emerging design, we advise releasing this model with guardrails in location. In this blog site, we will use Amazon Bedrock Guardrails to present safeguards, prevent hazardous content, and examine models against crucial security criteria. At the time of writing this blog site, for DeepSeek-R1 deployments on SageMaker JumpStart and Bedrock Marketplace, Bedrock Guardrails supports only the ApplyGuardrail API. You can produce multiple guardrails tailored to different use cases and apply them to the DeepSeek-R1 design, improving user experiences and standardizing safety controls across your generative AI applications.

Prerequisites

To deploy the DeepSeek-R1 design, you require access to an ml.p5e instance. To inspect if you have quotas for P5e, open the Service Quotas console and under AWS Services, select Amazon SageMaker, and validate you're using ml.p5e.48 xlarge for endpoint use. Make certain that you have at least one ml.P5e.48 xlarge instance in the AWS Region you are releasing. To ask for a limit increase, develop a limitation boost demand and reach out to your account team.

Because you will be deploying this design with Amazon Bedrock Guardrails, make certain you have the right AWS Identity and Gain Access To Management (IAM) approvals to utilize Amazon Bedrock Guardrails. For guidelines, see Set up authorizations to use guardrails for content filtering.

Implementing guardrails with the ApplyGuardrail API

Amazon Bedrock Guardrails permits you to present safeguards, avoid damaging material, and evaluate models against essential safety requirements. You can implement security procedures for the DeepSeek-R1 model using the Amazon Bedrock ApplyGuardrail API. This enables you to use guardrails to examine user inputs and model actions released on Amazon Bedrock Marketplace and SageMaker JumpStart. You can produce a guardrail utilizing the Amazon Bedrock console or the API. For the example code to create the guardrail, see the GitHub repo.

The general flow includes the following actions: First, the system gets an input for the model. This input is then processed through the ApplyGuardrail API. If the input passes the guardrail check, it's sent out to the model for reasoning. After getting the design's output, another guardrail check is used. If the output passes this last check, it's returned as the last result. However, if either the input or output is intervened by the guardrail, a message is returned indicating the nature of the intervention and whether it occurred at the input or output phase. The examples showcased in the following areas show using this API.

Deploy DeepSeek-R1 in Amazon Bedrock Marketplace

Amazon Bedrock Marketplace provides you access to over 100 popular, emerging, and specialized structure designs (FMs) through Amazon Bedrock. To gain access to DeepSeek-R1 in Amazon Bedrock, total the following steps:

1. On the Amazon Bedrock console, select Model brochure under Foundation designs in the navigation pane. At the time of writing this post, you can utilize the InvokeModel API to invoke the design. It does not support Converse APIs and other Amazon Bedrock tooling. 2. Filter for DeepSeek as a supplier and select the DeepSeek-R1 model.

The design detail page offers important details about the model's capabilities, rates structure, and implementation guidelines. You can discover detailed use directions, consisting of sample API calls and code snippets for combination. The design supports numerous text generation jobs, including material production, code generation, and question answering, using its support discovering optimization and CoT thinking capabilities. The page also consists of implementation alternatives and licensing details to assist you get going with DeepSeek-R1 in your applications. 3. To start utilizing DeepSeek-R1, select Deploy.

You will be prompted to configure the implementation details for DeepSeek-R1. The design ID will be pre-populated. 4. For Endpoint name, go into an endpoint name (between 1-50 alphanumeric characters). 5. For Number of instances, go into a number of instances (between 1-100). 6. For example type, pick your circumstances type. For optimum efficiency with DeepSeek-R1, higgledy-piggledy.xyz a GPU-based instance type like ml.p5e.48 xlarge is advised. Optionally, you can set up advanced security and facilities settings, consisting of virtual private cloud (VPC) networking, service role authorizations, and file encryption settings. For many utilize cases, the default settings will work well. However, for production releases, you may wish to review these settings to line up with your company's security and compliance requirements. 7. Choose Deploy to begin utilizing the model.

When the release is complete, you can test DeepSeek-R1's abilities straight in the Amazon Bedrock playground. 8. Choose Open in play ground to access an interactive interface where you can try out various triggers and change model parameters like temperature level and maximum length. When utilizing R1 with Bedrock's InvokeModel and Playground Console, utilize DeepSeek's chat template for ideal outcomes. For instance, material for reasoning.

This is an excellent method to explore the design's thinking and text generation capabilities before incorporating it into your applications. The play ground supplies instant feedback, helping you comprehend how the model reacts to numerous inputs and letting you tweak your triggers for optimum results.

You can quickly evaluate the design in the play ground through the UI. However, to conjure up the deployed design programmatically with any Amazon Bedrock APIs, you need to get the endpoint ARN.

Run inference utilizing guardrails with the deployed DeepSeek-R1 endpoint

The following code example shows how to carry out inference using a released DeepSeek-R1 model through Amazon Bedrock using the invoke_model and ApplyGuardrail API. You can produce a guardrail using the Amazon Bedrock console or the API. For the example code to create the guardrail, see the GitHub repo. After you have created the guardrail, utilize the following code to implement guardrails. The script initializes the bedrock_runtime client, configures reasoning parameters, and sends a request to generate text based upon a user prompt.

Deploy DeepSeek-R1 with SageMaker JumpStart

SageMaker JumpStart is an artificial intelligence (ML) center with FMs, integrated algorithms, and prebuilt ML solutions that you can deploy with just a couple of clicks. With SageMaker JumpStart, you can tailor pre-trained designs to your use case, with your data, and release them into production utilizing either the UI or SDK.

Deploying DeepSeek-R1 model through SageMaker JumpStart provides 2 practical methods: using the instinctive SageMaker JumpStart UI or carrying out programmatically through the SageMaker Python SDK. Let's check out both methods to help you choose the method that best matches your needs.

Deploy DeepSeek-R1 through SageMaker JumpStart UI

Complete the following steps to deploy DeepSeek-R1 using SageMaker JumpStart:

1. On the SageMaker console, select Studio in the navigation pane. 2. First-time users will be prompted to create a domain. 3. On the SageMaker Studio console, select JumpStart in the navigation pane.

The design web browser shows available models, with details like the supplier name and model capabilities.

4. Look for DeepSeek-R1 to view the DeepSeek-R1 model card. Each design card reveals essential details, including:

- Model name - Provider name

• Task classification (for instance, Text Generation). Bedrock Ready badge (if suitable), indicating that this design can be registered with Amazon Bedrock, permitting you to utilize Amazon Bedrock APIs to invoke the design
  
  5. Choose the model card to see the model details page.
  
  The design details page includes the following details:
  
  - The model name and provider details. Deploy button to release the model. About and Notebooks tabs with detailed details
  
  The About tab includes crucial details, such as:
  
  - Model description.
• License details.
• Technical requirements.
• Usage standards
  
  Before you deploy the design, it's suggested to review the design details and license terms to confirm compatibility with your usage case.
  
  6. Choose Deploy to proceed with deployment.
  
  7. For Endpoint name, use the automatically generated name or produce a customized one.

8. For Instance type ¸ select an instance type (default: ml.p5e.48 xlarge).
9. For Initial circumstances count, enter the number of circumstances (default: 1). Selecting suitable instance types and counts is important for cost and performance optimization. Monitor your implementation to adjust these settings as needed.Under Inference type, Real-time reasoning is chosen by default. This is optimized for sustained traffic and low latency.
10. Review all setups for accuracy. For this model, we highly recommend adhering to SageMaker JumpStart default settings and making certain that network isolation remains in place.
11. Choose Deploy to deploy the design.
    
    The release process can take numerous minutes to complete.
    
    When implementation is complete, your endpoint status will change to InService. At this point, the model is prepared to accept reasoning requests through the endpoint. You can keep an eye on the release development on the SageMaker console Endpoints page, which will show appropriate metrics and status details. When the implementation is total, you can conjure up the model using a SageMaker runtime customer and integrate it with your applications.
    
    Deploy DeepSeek-R1 using the SageMaker Python SDK
    
    To begin with DeepSeek-R1 using the SageMaker Python SDK, you will need to set up the SageMaker Python SDK and make certain you have the needed AWS approvals and environment setup. The following is a detailed code example that demonstrates how to deploy and use DeepSeek-R1 for reasoning programmatically. The code for deploying the design is offered in the Github here. You can clone the notebook and range from SageMaker Studio.
    
    You can run additional requests against the predictor:
    
    Implement guardrails and run inference with your SageMaker JumpStart predictor
    
    Similar to Amazon Bedrock, you can likewise utilize the ApplyGuardrail API with your SageMaker JumpStart predictor. You can produce a guardrail using the Amazon Bedrock console or the API, and implement it as displayed in the following code:
    
    Tidy up
    
    To prevent undesirable charges, finish the actions in this area to tidy up your resources.
    
    Delete the Amazon Bedrock Marketplace implementation
    
    If you released the model using Amazon Bedrock Marketplace, complete the following steps:
    
    1. On the Amazon Bedrock console, under Foundation models in the navigation pane, choose Marketplace implementations.
12. In the Managed deployments section, locate the endpoint you wish to delete.
13. Select the endpoint, and on the Actions menu, choose Delete.
14. Verify the endpoint details to make certain you're deleting the right deployment: 1. Endpoint name.
15. Model name.
16. Endpoint status
    
    Delete the SageMaker JumpStart predictor
    
    The SageMaker JumpStart design you deployed will sustain costs if you leave it running. Use the following code to erase the endpoint if you desire to stop sustaining charges. For more details, see Delete Endpoints and Resources.
    
    Conclusion
    
    In this post, we explored how you can access and deploy the DeepSeek-R1 design using Bedrock Marketplace and SageMaker JumpStart. Visit SageMaker JumpStart in SageMaker Studio or Amazon Bedrock Marketplace now to get going. For more details, refer to Use Amazon Bedrock tooling with Amazon SageMaker JumpStart designs, SageMaker JumpStart pretrained models, Amazon SageMaker JumpStart Foundation Models, Amazon Bedrock Marketplace, and Getting begun with Amazon SageMaker JumpStart.
    
    About the Authors
    
    Vivek Gangasani is a Lead Specialist Solutions Architect for Inference at AWS. He helps emerging generative AI companies construct ingenious services using AWS services and accelerated calculate. Currently, he is focused on establishing methods for fine-tuning and enhancing the reasoning performance of big language models. In his spare time, Vivek takes pleasure in hiking, enjoying films, and attempting various foods.
    
    Niithiyn Vijeaswaran is a Generative AI Specialist Solutions Architect with the Third-Party Model Science group at AWS. His area of focus is AWS AI accelerators (AWS Neuron). He holds a Bachelor's degree in Computer technology and Bioinformatics.
    
    Jonathan Evans is an Expert Solutions Architect dealing with generative AI with the Third-Party Model Science team at AWS.
    
    Banu Nagasundaram leads product, engineering, and strategic collaborations for Amazon SageMaker JumpStart, SageMaker's artificial intelligence and generative AI hub. She is enthusiastic about developing options that help consumers accelerate their AI journey and unlock organization value.