Sold by: Preferred Networks, Inc.
Deployed on AWS
Deploy PLaMo API server to your environment
Overview
PLaMo is a large language model (LLM) that achieves world-leading performance in Japanese language capabilities, architected and built entirely from the ground up by Preferred Networks Group.
Now we support 4 bit quantize version only
Highlights
- PLaMo has achieved accuracy surpassing GPT-4 in major Japanese benchmarks such as Jaster. In addition to Japanese responses, PLaMo also demonstrates excellent performance in Japanese-English translation.
Details
Sold by
Categories
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
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.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.12xlarge Inference (Batch) Recommended | Model inference on the ml.g5.12xlarge instance type, batch mode | $10.00 |
ml.p4d.24xlarge Inference (Real-Time) Recommended | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $10.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $10.00 |
ml.g5.48xlarge Inference (Batch) | Model inference on the ml.g5.48xlarge instance type, batch mode | $10.00 |
ml.g5.24xlarge Inference (Batch) | Model inference on the ml.g5.24xlarge instance type, batch mode | $10.00 |
ml.g5.12xlarge Inference (Real-Time) | Model inference on the ml.g5.12xlarge instance type, real-time mode | $10.00 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $10.00 |
ml.g5.24xlarge Inference (Real-Time) | Model inference on the ml.g5.24xlarge instance type, real-time mode | $10.00 |
Dimensions summary
You deploy this model in your own AWS environment and pay by the hour for each instance you run. Pricing splits into two inference modes: batch, for processing groups of requests, and real-time, for immediate responses. Within each mode, you choose an instance size. Batch runs on ml.m5.4xlarge, ml.g5.12xlarge, ml.g5.24xlarge, and ml.g5.48xlarge. Real-time runs on ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, and ml.p4d.24xlarge. Larger instances carry more compute and higher hourly rates. Your total cost scales with the instance size you pick and the hours it stays active.
Top-of-mind questions for buyers
Batch mode processes groups of requests together, suited to bulk jobs where you can wait for results. Real-time mode returns immediate responses, suited to interactive uses like chat. Each mode meters the same way, by instance-hour. You pick the mode and instance size that match your workload.
You pay the hourly software rate only while an instance runs. Stopped instances stop accruing the hourly software charge. Note that AWS may still bill underlying storage or other resource fees for stopped instances, separate from this listing's software rate.
No upfront fee applies. You pay per instance-hour as you run. Any data you send to the model in your AWS environment stays within your account and is not used for training. Charges cover model inference on the instance you select.
plamo.preferredai.jp
Helpful?
Vendor refund policy
We doesn't support yet
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
PLaMo 4bit quantize version
Additional details
Inputs
- Summary
Please send thease paramests as json.
We have many option parameters, you can find full docs in https://plamo.preferredai.jp/docs
- Input MIME type
- application/json
{
"messages": [
{
"role": "system",
"content": "あなたは旅行アドバイザーです"
},
{
"role": "user",
"content": "金沢で朝から夕方まで1日のおすすめの観光ルートを教えて下さい"
}
]
}
https://pfn-marketplace-sagemaker.s3.ap-northeast-1.amazonaws.com/test/in.txt
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
model | Set model name you can choice `plamo-prime` only | Default value: plamo-prime
Type: FreeText | No |
messages | Set chat messages
| Type: FreeText
Limitations: You should set message object please see our docs | Yes |
Resources
Vendor resources
Support
Vendor 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.
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.