Amazon Sagemaker
Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.
Hierarchical Classifier using LLMs
By:
Latest Version:
2.1
Hierarchical classifier using LLMs designed to classify text into multiple levels of categories based on predefined hierarchical structures.
Product Overview
The idea is to take a textual data as input (such as a IT incident tickets, customer helpdesk queries, or documents/emails) and predict the appropriate category at each level of a hierarchy. This system is useful when dealing with data that has multiple levels of granularity, and it's crucial for organizing information based on more specific or broad categories. This trainable listing fine-tunes Phi-3 model, and the resulting LoRA adapters can be directly used for inference. Users must provide datasets with textual descriptions of any specific domain and their corresponding multi-level labels, ensuring the label count does not surpass 256.
Key Data
Version
By
Type
Algorithm
Highlights
This solution streamlines classification workflows by automatically mapping textual input to the most relevant hierarchical categories, reducing manual tagging efforts and accelerating decision-making processes across diverse industries.
Using lora adapters, our solution enables efficient fine-tuning of Phi-3 model while minimizing computational overhead. The resulting trainable LoRA adapters can be seamlessly applied in multi-adapter settings, providing flexibility for deployment across various use cases.
Mphasis DeepInsights is a cloud-based cognitive computing platform that offers data extraction & predictive analytics capabilities. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us
Pricing Information
Use this tool to estimate the software and infrastructure costs based your configuration choices. Your usage and costs might be different from this estimate. They will be reflected on your monthly AWS billing reports.
Contact us to request contract pricing for this product.
Estimating your costs
Choose your region and launch option to see the pricing details. Then, modify the estimated price by choosing different instance types.
Version
Region
Software Pricing
Algorithm Training$2/hr
running on ml.g5.4xlarge
Model Realtime Inference$2.00/hr
running on ml.p2.8xlarge
Model Batch Transform$2.00/hr
running on ml.p2.8xlarge
Infrastructure PricingWith Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
With Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
SageMaker Algorithm Training$2.03/host/hr
running on ml.g5.4xlarge
SageMaker Realtime Inference$8.64/host/hr
running on ml.p2.8xlarge
SageMaker Batch Transform$8.64/host/hr
running on ml.p2.8xlarge
Algorithm Training
For algorithm training in Amazon SageMaker, the software is priced based on hourly pricing that can vary by instance type. Additional infrastructure cost, taxes or fees may apply.InstanceType | Algorithm/hr | |
|---|---|---|
ml.g5.8xlarge | $2.00 | |
ml.g5.12xlarge | $2.00 | |
ml.g5.2xlarge | $2.00 | |
ml.g5.4xlarge Vendor Recommended | $2.00 | |
ml.g5.48xlarge | $2.00 | |
ml.g5.16xlarge | $2.00 | |
ml.g5.24xlarge | $2.00 |
Usage Information
Training
For model finetuning, the data can be uploaded in a folder as train.csv file. - Adhere to the naming convention mentioned below for finetuning the model. - The textual description must have the column name DESCRIPTION - The categories must have the column names like CATEGORY_1, CATEGORY_2, CATEGORY_3, CATEGORY_4 - The total number of labels in all the category columns together must not exceed 256 - The number of datapoints for training should not exceed 10,000 rows.
Channel specification
Fields marked with * are required
train
*Input modes: File
Content types: text/csv
Compression types: None
Hyperparameters
Fields marked with * are required
epochs
*Epochs hyperparameter
Type: Integer
Tunable: No
Model input and output details
Input
Summary
The input file should be train.csv
Limitations for input type
The train.csv with maximum of 10,000 rows.
Input MIME type
text/csvSample input data
Output
Summary
The output from finetuned model is a lora adapter, which will be used at the time of endpoint creation.
Output MIME type
application/gzipSample output data
Sample notebook
Additional Resources
End User License Agreement
By subscribing to this product you agree to terms and conditions outlined in the product End user License Agreement (EULA)
Support Information
Hierarchical Classifier using LLMs
For any assistance reach out to us at:
AWS Infrastructure
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.
Learn MoreRefund Policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Customer Reviews
There are currently no reviews for this product.
View allWrite a review
Share your thoughts about this product.
Write a customer review