Select your cookie preferences

We use essential cookies and similar tools that are necessary to provide our site and services. We use performance cookies to collect anonymous statistics, so we can understand how customers use our site and make improvements. Essential cookies cannot be deactivated, but you can choose “Customize” or “Decline” to decline performance cookies.

If you agree, AWS and approved third parties will also use cookies to provide useful site features, remember your preferences, and display relevant content, including relevant advertising. To accept or decline all non-essential cookies, choose “Accept” or “Decline.” To make more detailed choices, choose “Customize.”

Sign in
Your Saved List Become a Channel Partner Sell in AWS Marketplace Amazon Web Services Home Help

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.

product logo

Cohere Classification Finetuning - Multi

By:
Latest Version:
v2.0.3
Classification finetuning supports single / multi-label classification based on semantic meaning of text against a predefined set of labels.

    Product Overview

    Cohere’s Classification Finetuning enables you to train and deploy classification models with a few lines of code. Using as few as 2 examples per label, users are able to train custom models to classify text based on semantic meaning (results will vary depending on the classification task at hand - for more complex and nuanced tasks we recommend more than 2 examples).

    Key Data

    Version
    Show other versions
    Type
    Algorithm
    Fulfillment Methods
    Amazon SageMaker

    Highlights

    • Cohere supports the training of single and multi-label classification models

    • This offering supports cross-lingual classification - classify incoming text irrespective of the language provided during training.

    • Classification, Finetuning, Multilingual, Text Embeddings

    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$11.41/hr

    running on ml.g5.xlarge

    Model Realtime Inference$5.97/hr

    running on ml.g4dn.xlarge

    Model Batch Transform$5.97/hr

    running on ml.g4dn.xlarge

    Infrastructure 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$1.408/host/hr

    running on ml.g5.xlarge

    SageMaker Realtime Inference$0.736/host/hr

    running on ml.g4dn.xlarge

    SageMaker Batch Transform$0.736/host/hr

    running on ml.g4dn.xlarge

    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.xlarge
    Vendor Recommended
    $11.41
    ml.g5.2xlarge
    $12.28
    ml.g4dn.xlarge
    $5.97
    ml.g4dn.2xlarge
    $7.62

    Usage Information

    Training

    The data must be in JSONL format, with "text" and "label" keys. For single label classification, the "label" value must be an integer or string. For multi label classification, the "label" value must be a list of integers or a list of strings. For examples which do not correspond to any label, leave the list empty.

    E.g. for multilabel classification: {"text":"This sentence talks about pasta and pizza", "label":[0,1]} {"text":"This sentence does not talk about food", "label":[]} {"text":"Pasta is a great dish", "label":[0]} {"text":"Could I get a slice please?", "label":[1]}

    Channel specification

    Fields marked with * are required

    training

    *
    Input modes: File
    Content types: -
    Compression types: None

    evaluation

    Input modes: File
    Content types: -
    Compression types: None

    Hyperparameters

    Fields marked with * are required

    name

    *
    Name of the model to be trained
    Type: FreeText
    Tunable: No

    Model input and output details

    Input

    Summary

    The model accepts JSON requests that specify the input texts to be classified and the model to use. E.g. {"texts": ["hello world"], "model_id": "BASE"}

    It is better to use the co.classify() call to send requests, as in https://github.com/cohere-ai/cohere-sagemaker/blob/main/notebooks/Deploy%20classification%20model.ipynb

    Input MIME type
    application/json
    Sample input data
    {
      "texts": [
        "hello world"
      ],
      "model_id": "BASE"
    }

    Output

    Summary

    The output format is a list of:

    • labels in the single-label classification case
    • list of labels in the multi-label classification case
    Output MIME type
    text/plain
    Sample output data
    [1, 0]

    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

    Cohere Classification Finetuning - Multi

    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 More

    Refund Policy

    No refunds.

    Customer Reviews

    There are currently no reviews for this product.
    View all