Sold by: Arcee
Deployed on AWS
Arcee-Lite is a compact yet powerful 1.5B parameter language model developed by Arcee.ai.
Overview
Arcee-Lite was developed by Arcee.ai as part of the DistillKit open-source project. Despite its small size, Arcee-Lite demonstrates impressive performance, particularly in the MMLU (Massive Multitask Language Understanding) benchmark. Arcee-Lite is a distillation of the phi-3-medium 14B model into a Qwen2 1.5 model. It has a 32 KB context size.
IMPORTANT INFORMATION: Once you have subscribed to the model, we strongly recommend that you deploy it with our sample notebook at https://github.com/arcee-ai/aws-samples/blob/main/model_package_notebooks/sample-notebook-arcee-lite-on-sagemaker.ipynb .
Highlights
- Arcee-Lite is suitable for a wide range of applications where a balance between model size and performance is crucial: * Embedded systems * Mobile applications * Edge computing * Resource-constrained environments
- Arcee-Lite showcases remarkable capabilities for its size: * Achieves a 55.93 score on the MMLU benchmark * Demonstrates exceptional performance across various tasks
- The model generates over 100 tokens per second on ml.g5.2xlarge.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
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
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimensions summary
Arcee Lite is free to use, so you pay only for the AWS compute you select. You choose an instance type to run model inference. Fourteen dimensions cover real-time inference across compute-optimized (c6i, c7i) and GPU (g5, g6) instances, billed per host hour. Two dimensions cover batch inference on p3 GPU instances, also billed per host hour. Larger instance sizes within a family carry more capacity. Pick real-time mode for on-demand responses or batch mode for grouped processing. Your cost scales with the instance size you run and the hours it runs.
Top-of-mind questions for buyers
One host hour is one running hour of the AWS instance you select. Charges accrue only while the instance runs. A stopped or terminated instance stops the software meter. Underlying AWS storage or reserved capacity may still bill separately through AWS, but the software itself meters running time only.
Both meter per host hour of the selected instance. Real-time mode keeps an instance running to answer requests on demand, so you pay for uptime whether or not requests arrive. Batch mode runs an instance to process grouped inputs, so you pay for the processing duration. Real-time suits steady traffic; batch suits scheduled jobs.
You pay the host-hour rate for whichever instance you run. A larger size in a family provides more capacity but carries a different per-hour rate. Cost changes when you select a new instance type, not automatically. You control cost by choosing the instance size and the number of hours it runs.
arcee.ai
Helpful?
Vendor refund policy
This product is offered for free. If there are any questions, please contact us for further clarifications.
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.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This version is configured for single-GPU instances of the g5 and g6 families, as well as CPU instances of the c6i and c7i families. Context size is 4 KB and the OpenAI Messages API is enabled.
Additional details
Inputs
- Summary
You can invoke the model using the OpenAI Messages AI. Please see the sample notebook for details.
- Input MIME type
- application/json, application/jsonlines
{
"messages": [
{
"role": "system",
"content": "As a friendly technical assistant engineer, answer the question in detail.",
},
{"role": "user", "content": "Why are transformers better models than LSTM?"},
],
"max_tokens": 256
}
https://github.com/arcee-ai/aws-samples/blob/main/model_package_notebooks/sample-notebook-arcee-lite-on-sagemaker.ipynb
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
OpenAI Messages API | Please see sample notebook. | Type: FreeText | Yes |
Resources
Vendor resources
Support
Vendor support
IMPORTANT INFORMATION: Once you have subscribed to the model, we strongly recommend that you deploy it with our sample notebook at https://github.com/arcee-ai/aws-samples/blob/main/model_package_notebooks/sample-notebook-arcee-lite-on-sagemaker.ipynb . This is the best way to guarantee proper configuration.
Bugs, questions, feature requests: please create an issue in the aws-samples repository on Github.
Contact: julien@arcee.ai
AWS infrastructure support
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.
Similar products
Llama-3.1-SuperNova-Lite is an 8B parameter model developed by Arcee.ai.
Enterprise-grade LLM offering deep customization, seamless integration, and top-tier security & compliance for businesses.
Virtuoso Medium is a general-purpose, 32-billion parameter model developed by Arcee AI.
Customer reviews
No customer reviews yet
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.