Sold by: ABEJA, Inc.Â
Deployed on AWS
The ABEJA Mixtral-8x7B-v0.1-japanese model is specifically designed and optimized for the Japanese language.
Overview
The ABEJA Mixtral-8x7B-v0.1-japanese model is a specialized version of Mixtral-8x7B-v0.1, enhanced through continued pretraining to expand its Japanese vocabulary. This adaptation improves the model’s ability to understand and generate natural Japanese text with greater accuracy and fluency.
As part of a NEDO-funded project, ABEJA is actively researching and developing large language models (LLMs). Within the GENIAC project, the team focused on refining Mistral-8x7B by extending its Japanese linguistic capabilities, ensuring better comprehension and contextual accuracy in various applications.
Highlights
- The ABEJA Mixtral-8x7B-v0.1-japanese model is an enhanced version of Mixtral-8x7B-v0.1, optimized through continued pretraining for improved Japanese vocabulary, accuracy, and fluency.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
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.
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)Â .
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
Released on February 1, 2025
Additional details
Inputs
- Summary
The model returns JSON object, which contains list of message.
data = {
"messages": [
{"role":"user", "content": "Hello"}
]
}
https://abeja-llm-sample-input-data.s3.us-east-2.amazonaws.com/data.json
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
messages | [{"role":"user", "content": "Hello"}] | Type: FreeText | Yes |
Resources
Vendor resources
Support
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
ABEJA, as an AWS Machine Learning Competency Partner, is driving a digital platform business that provides end-to-end AI implementation support, including generative AI, and operations based on the ABEJA Platform. The following is an outline of the professional services available through AWS Marketplace.
A large Japanese language corpus created through preprocessing Common Crawl data
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.