This is a single-click AMI package of DeepSeek-Coder-33B, which is among DeepSeek Coder series of large code language models, pre-trained on 2 trillion tokens of 87% code and 13% natural language text. DeepSeek Coder models are trained with a 16,000 token window size and an extra fill-in-the-blank task to enable project-level code completion and infilling. DeepSeek Coder achieves state-of-the-art performance on various code generation benchmarks compared to other open-source code models.
Deepseek-coder-33b-instruct is a 33B parameter model initialized from deepseek-coder-33b-base and fine-tuned on 2B tokens of instruction data.
Massive Training Data: Trained from scratch fon 2T tokens, including 87% code and 13% linguistic data in both English and Chinese languages.
Highly Flexible & Scalable: Enabling users to choose the setup most suitable for their requirements.
Superior Model Performance: State-of-the-art performance among publicly available code models on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS benchmarks.
Advanced Code Completion Capabilities: A window size of 16K and a fill-in-the-blank task, supporting project-level code completion and infilling tasks.
Key Features:
Ready-to-Deploy: Unlike the raw DeepSeek models, the AMI version facilitates an immediate launch, eliminating intricate setup processes.
API Integration: Integrated with a robust API, it ensures a seamless interface with a myriad of applications, amplifying flexibility."
Highlights
Easy Integration: Designed for interoperability, this AMI effortlessly aligns with the OpenAI landscape and offers seamless API connections, ensuring smooth operations across diverse platforms.
Effortless Deployment: Designed for ease-of-use, this AMI provides users with a hassle-free setup experience, ensuring quick implementation without the complexities.
Pay-as-You-Go Flexibility: Enjoy cost efficiency with a pay-as-you-go pricing model.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time. Alternatively, you can pay upfront for a contract, which typically covers your anticipated usage for the contract duration. Any usage beyond contract will incur additional usage-based costs.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
You pay by the hour for the EC2 instance type you run this software on. There are two options, each tied to a different hardware size. The g5g.16xlarge rate covers one class of GPU-backed instance. The g5g.metal rate covers a bare-metal instance with more capacity. Both are billed per hour, so your total cost depends on the instance you choose and how long you keep it running. You can stop the instance to pause charges and restart it later.
Top-of-mind questions for buyers
What compute do the g5g.16xlarge and g5g.metal rates map to?
Each rate maps to a specific EC2 instance size the software runs on. The g5g.16xlarge covers one GPU-backed instance class. The g5g.metal covers a bare-metal instance. You pick one instance type at deployment, and the hourly software charge follows the type you launch.
Am I charged when I stop the instance to pause work?
The hourly software charge meters running time only. When you stop the instance, software charges pause. You can restart it later from the EC2 console. Note that stored data on the instance may still incur underlying AWS storage fees while it is stopped.
Do I need to pick a vCPU quota or other setup before launching?
Yes. You need an AWS account with permissions and enough vCPU limit to launch a g5g instance. If you hit a vCPU quota error, you must request a limit increase. Deployment uses a CloudFormation template where you set the instance type and network options.
blogs.meetrix.io
Helpful?
Vendor refund policy
We do not currently support refunds, but you can cancel at any time.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Deepseek coder is capable of generating text, answering questions, generating content, and performing a range of text-related tasks in response to the provided prompts. Specially for programming languages and computer science related questions.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
First Release
Additional details
Usage instructions
Template components
CloudFormation template
Usage instructions
Click the "Continue to Subscribe" button. After subscribing, you will need to accept the terms and conditions. Click on "Accept Terms" to proceed.
Please wait for a few minutes while the processing takes place. Once it's completed, click on "Continue to Configuration".
IAM Role is set up and configured with the necessary permissions to assume the role for the Deepseekcoder service. The IAM Policy is created and responsible for accessing Route53 and creating Letsencrypt SSL certificates. Apart from that volume permissions also given for changing volume type of instance.
Access the application via a browser at http://<your domain name>/docs or http://<Public IPv4 address>/docs.
Product will try to setup SSL based on provided domain name, if domain hosted on route53. If the automatic SSL creation unsuccesful then you have to point domain name into server ip, ssh into server and run /root/certificate_generate_standalone.sh. Admin email is also using for generate SSL certificates.
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.