Today, we are thrilled 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 deploy DeepSeek AI's first-generation frontier design, DeepSeek-R1, along with the distilled versions ranging from 1.5 to 70 billion parameters to construct, experiment, and properly scale your generative AI concepts on AWS.

In this post, we demonstrate how to start with DeepSeek-R1 on Amazon Bedrock Marketplace and . You can follow similar steps to release the distilled versions of the designs too.

Overview of DeepSeek-R1

DeepSeek-R1 is a large language model (LLM) developed by DeepSeek AI that utilizes support finding out to improve thinking capabilities through a multi-stage training process from a DeepSeek-V3-Base structure. A key identifying feature is its support learning (RL) action, which was utilized to improve the model's actions beyond the standard pre-training and fine-tuning process. By integrating RL, DeepSeek-R1 can adapt better to user feedback and objectives, eventually boosting both relevance and clarity. In addition, DeepSeek-R1 utilizes a chain-of-thought (CoT) approach, meaning it's equipped to break down intricate queries and factor through them in a detailed manner. This directed reasoning procedure allows the model to produce more accurate, transparent, and detailed responses. This design integrates RL-based fine-tuning with CoT abilities, aiming to generate structured reactions while focusing on interpretability and user interaction. With its wide-ranging abilities DeepSeek-R1 has caught the market's attention as a flexible text-generation model that can be integrated into numerous workflows such as agents, rational thinking and information analysis tasks.

DeepSeek-R1 uses a Mixture of Experts (MoE) architecture and is 671 billion parameters in size. The MoE architecture allows activation of 37 billion parameters, enabling efficient inference by routing queries to the most appropriate expert "clusters." This technique enables the design to specialize in various problem domains while maintaining overall performance. DeepSeek-R1 needs a minimum of 800 GB of HBM memory in FP8 format for reasoning. In this post, we will utilize an ml.p5e.48 xlarge instance to release the model. ml.p5e.48 xlarge includes 8 Nvidia H200 GPUs offering 1128 GB of GPU memory.

DeepSeek-R1 distilled models bring the reasoning capabilities 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 sized, more efficient models to mimic the habits and reasoning patterns of the larger DeepSeek-R1 model, utilizing it as a teacher model.

You can deploy DeepSeek-R1 model either through SageMaker JumpStart or Bedrock Marketplace. Because DeepSeek-R1 is an emerging model, we recommend releasing this model with guardrails in place. In this blog site, we will utilize Amazon Bedrock Guardrails to present safeguards, avoid damaging material, and examine designs against crucial security criteria. At the time of writing this blog site, for DeepSeek-R1 releases on SageMaker JumpStart and Bedrock Marketplace, Bedrock Guardrails supports just the ApplyGuardrail API. You can create multiple guardrails tailored to various usage cases and use them to the DeepSeek-R1 design, enhancing user experiences and standardizing safety controls across your generative AI applications.

Prerequisites

To deploy the DeepSeek-R1 model, you need access to an ml.p5e circumstances. To inspect if you have quotas for P5e, open the Service Quotas console and setiathome.berkeley.edu under AWS Services, select Amazon SageMaker, and verify you're using ml.p5e.48 xlarge for endpoint usage. Make certain that you have at least one ml.P5e.48 xlarge instance in the AWS Region you are deploying. To ask for a limit boost, produce a limitation increase demand and connect 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) permissions to utilize Amazon Bedrock Guardrails. For guidelines, see Establish consents to utilize guardrails for material filtering.

Implementing guardrails with the ApplyGuardrail API

Amazon Bedrock Guardrails enables you to introduce safeguards, avoid damaging content, and assess models against essential security criteria. You can carry out precaution for the DeepSeek-R1 model using the Amazon Bedrock ApplyGuardrail API. This permits you to use guardrails to assess user inputs and design responses deployed on Amazon Bedrock Marketplace and SageMaker JumpStart. You can create 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 steps: 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 design for inference. After getting the model's output, another guardrail check is applied. If the output passes this final check, it's returned as the last outcome. However, if either the input or output is stepped in by the guardrail, a message is returned suggesting the nature of the intervention and whether it occurred at the input or output stage. The examples showcased in the following sections demonstrate reasoning utilizing this API.

Deploy DeepSeek-R1 in Amazon Bedrock Marketplace

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

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

The model detail page supplies essential details about the model's capabilities, pricing structure, and application guidelines. You can discover detailed use guidelines, consisting of sample API calls and code snippets for combination. The model supports numerous text generation jobs, including material development, code generation, and question answering, using its support finding out optimization and CoT thinking capabilities. The page likewise consists of deployment options and licensing details to help you get started with DeepSeek-R1 in your applications. 3. To start using DeepSeek-R1, pick Deploy.

You will be triggered to set up the release details for DeepSeek-R1. The model ID will be pre-populated. 4. For Endpoint name, go into an endpoint name (in between 1-50 alphanumeric characters). 5. For Number of instances, get in a variety of instances (in between 1-100). 6. For Instance type, pick your circumstances type. For optimum efficiency with DeepSeek-R1, a GPU-based instance type like ml.p5e.48 xlarge is recommended. Optionally, you can set up advanced security and facilities settings, consisting of virtual personal cloud (VPC) networking, service role approvals, and file encryption settings. For most use cases, the default settings will work well. However, for production deployments, you might 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 implementation is total, you can check DeepSeek-R1's abilities straight in the Amazon Bedrock playground. 8. Choose Open in playground to access an interactive user interface where you can experiment with different triggers and adjust model criteria like temperature and maximum length. When utilizing R1 with Bedrock's InvokeModel and Playground Console, utilize DeepSeek's chat template for optimal outcomes. For example, content for inference.

This is an outstanding method to explore the design's reasoning and text generation capabilities before incorporating it into your applications. The playground supplies immediate feedback, helping you comprehend how the design responds to numerous inputs and letting you fine-tune your triggers for optimum outcomes.

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

Run inference utilizing guardrails with the released DeepSeek-R1 endpoint

The following code example demonstrates how to carry out reasoning utilizing a deployed DeepSeek-R1 model through Amazon Bedrock utilizing the invoke_model and ApplyGuardrail API. You can create a guardrail using the Amazon Bedrock console or the API. For the example code to develop the guardrail, see the GitHub repo. After you have produced the guardrail, use the following code to carry out guardrails. The script initializes the bedrock_runtime client, configures reasoning parameters, and sends out a request to produce text based on a user timely.

Deploy DeepSeek-R1 with SageMaker JumpStart

SageMaker JumpStart is an artificial intelligence (ML) center with FMs, built-in algorithms, and prebuilt ML options that you can deploy with just a few clicks. With SageMaker JumpStart, you can tailor pre-trained designs to your use case, with your data, and deploy them into production using either the UI or SDK.

Deploying DeepSeek-R1 design through SageMaker JumpStart provides two convenient methods: using the intuitive SageMaker JumpStart UI or carrying out programmatically through the SageMaker Python SDK. Let's explore both approaches to assist you pick the technique that best matches your requirements.

Deploy DeepSeek-R1 through SageMaker JumpStart UI

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

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

The design web browser shows available designs, with details like the company name and design abilities.

4. Look for DeepSeek-R1 to see the DeepSeek-R1 design card. Each design card reveals crucial details, including:

- Model name

• Provider name
• Task category (for instance, Text Generation). Bedrock Ready badge (if relevant), suggesting that this design can be signed up with Amazon Bedrock, allowing you to utilize Amazon Bedrock APIs to conjure up the model
  
  5. Choose the design card to see the model details page.
  
  The design details page consists of the following details:
  
  - The design name and company details. Deploy button to release the design. About and Notebooks tabs with detailed details
  
  The About tab includes essential details, such as:
  
  - Model description.
• License details.
• Technical specifications.
• Usage standards
  
  Before you deploy the design, it's advised to evaluate the model details and license terms to confirm compatibility with your usage case.
  
  6. Choose Deploy to proceed with release.
  
  7. For Endpoint name, use the automatically generated name or create a customized one.

8. For Instance type ¸ pick an instance type (default: ml.p5e.48 xlarge).
9. For Initial circumstances count, get in the variety of instances (default: 1). Selecting appropriate instance types and counts is vital for expense and efficiency optimization. Monitor your release to adjust these settings as needed.Under Inference type, Real-time reasoning is chosen by default. This is enhanced for sustained traffic and low latency.
10. Review all setups for precision. For this model, we highly recommend sticking to SageMaker JumpStart default settings and making certain that network isolation remains in location.
11. Choose Deploy to release the design.
    
    The implementation procedure can take numerous minutes to complete.
    
    When deployment is total, your endpoint status will alter to InService. At this moment, the design is prepared to accept inference demands through the endpoint. You can keep track of the implementation development on the SageMaker console Endpoints page, which will display appropriate metrics and status details. When the implementation is complete, you can invoke the design utilizing a SageMaker runtime client and incorporate it with your applications.
    
    Deploy DeepSeek-R1 utilizing 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 required AWS consents and environment setup. The following is a detailed code example that shows how to deploy and utilize DeepSeek-R1 for inference programmatically. The code for deploying the model is supplied in the Github here. You can clone the notebook and range from SageMaker Studio.
    
    You can run extra requests against the predictor:
    
    Implement guardrails and run reasoning with your SageMaker JumpStart predictor
    
    Similar to Amazon Bedrock, you can also use the ApplyGuardrail API with your SageMaker JumpStart predictor. You can produce a guardrail utilizing the Amazon Bedrock console or the API, and implement it as displayed in the following code:
    
    Clean up
    
    To avoid unwanted charges, complete the steps in this area to clean up your resources.
    
    Delete the Amazon Bedrock Marketplace release
    
    If you deployed the model using Amazon Bedrock Marketplace, complete the following steps:
    
    1. On the Amazon Bedrock console, under Foundation designs in the navigation pane, choose Marketplace deployments.
12. In the Managed deployments area, find the endpoint you want to erase.
13. Select the endpoint, and on the Actions menu, select Delete.
14. Verify the endpoint details to make certain you're erasing the appropriate release: 1. Endpoint name.
15. Model name.
16. Endpoint status
    
    Delete the SageMaker JumpStart predictor
    
    The SageMaker JumpStart design you released will sustain costs if you leave it running. Use the following code to delete the endpoint if you want to stop sustaining charges. For more details, see Delete Endpoints and Resources.
    
    Conclusion
    
    In this post, we checked out how you can access and deploy the DeepSeek-R1 model utilizing 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 Starting with Amazon SageMaker JumpStart.
    
    About the Authors
    
    Vivek Gangasani is a Lead Specialist Solutions Architect for Inference at AWS. He helps emerging generative AI business build innovative services using AWS services and sped up calculate. Currently, he is focused on establishing techniques for fine-tuning and enhancing the inference performance of big language models. In his complimentary time, Vivek takes pleasure in treking, viewing motion pictures, and attempting different cuisines.
    
    Niithiyn Vijeaswaran is a Generative AI Specialist Solutions Architect with the Third-Party Model Science group at AWS. His location of focus is AWS AI accelerators (AWS Neuron). He holds a Bachelor's degree in Computer Science and Bioinformatics.
    
    Jonathan Evans is a Professional Solutions Architect dealing with generative AI with the Third-Party Model Science group at AWS.
    
    Banu Nagasundaram leads product, engineering, and strategic partnerships for Amazon SageMaker JumpStart, SageMaker's artificial intelligence and generative AI hub. She is enthusiastic about developing services that help clients accelerate their AI journey and unlock business worth.