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
Sign in
or
Create a new account
About
Categories
Delivery Methods
Solutions
Resources
 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

Medical LLM - 24B Free trial

By:
John Snow Labs
Latest Version:
1.0
Medical model offering top-tier depth and accuracy in processing complex medical cases and literature, ideal for specialized medical use
Continue to Subscribe

    Product Overview

    Matching the performance of industry leaders with quicker inference times and lower deployment costs, the model is ideal for healthcare institutions needing medical analysis without substantial computational resources. Trained on a wide array of medical texts, the model is highly adept at summarizing complex clinical information, answering medical questions, and summarizing detailed clinical notes and various medical reports. Its summarization capability enhances efficiency while retaining essential details. The model's ability to answer both open and closed medical queries with precise, context-specific responses further aids in clinical decision-making. It provides physicians with rapid insights into a patient's medical history, enabling timely and well-informed decisions. Optimized for Retrieval-Augmented Generation (RAG), it works effectively with healthcare databases, EHR systems, and scientific literature repositories to improve the quality of responses.

    Key Data

    Version
    1.0
    Usage Instructions
    Release Notes
    By
    John Snow Labs
    Categories
    Generative AI
    Summarization-Text
    Healthcare & Life Sciences
    Type
    Model Package
    Fulfillment Methods
    Amazon SageMaker

    Highlights

    • Real-Time Inference

      • Instance Type: ml.g5.48xlarge
      • Maximum Model Length: 32K tokens

      Tokens per Second during real-time inference:

      • Summarization: up to 427 tokens per second
      • QA: up to 1,292 tokens per second

    • Batch Transform

      • Instance Type: ml.g5.48xlarge
      • Maximum Model Length: 32K tokens

      Tokens per Second during batch transform operations:

      • Summarization: up to 50 tokens per second
      • QA: up to 162 tokens per second

    • Accuracy:

      • Achieves 82.83% OpenMed average, matching GPT-4 (82.85%) with fraction of parameters
      • Outperforms Med-PaLM-2 in medical genetics (92% vs 90%) and college medicine (79.19% vs 80.9%)
      • Matches GPT-4's clinical knowledge accuracy (86.04%)
      • Surpasses Med-PaLM-1 across all benchmarks by +8.13% average
      • Processes medical MCQAs with 70.27% accuracy, comparable to Med-PaLM-2 (71.3%)
      • Maintains competitive performance with leading models while requiring significantly less compute

    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

    Model Realtime Inference$19.96/hr

    running on ml.g5.48xlarge

    Model Batch Transform$19.96/hr

    running on ml.g5.48xlarge

    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 Realtime Inference$20.36/host/hr

    running on ml.g5.48xlarge

    SageMaker Batch Transform$20.36/host/hr

    running on ml.g5.48xlarge

    About Free trial

    Try this product for 15 days. There will be no software charges, but AWS infrastructure charges still apply. Free Trials will automatically convert to a paid subscription upon expiration.

    Model Realtime Inference

    For model deployment as Real-time endpoint 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
    Realtime Inference/hr
    ml.g6e.12xlarge
    $19.96
    ml.g6e.24xlarge
    $19.96
    ml.p4d.24xlarge
    $19.96
    ml.g6e.48xlarge
    $19.96
    ml.g5.48xlarge
    Vendor Recommended
    $19.96
    ml.p5.48xlarge
    $19.96

    Usage Information

    Model input and output details

    Input

    Summary

    To use the model, provide input in one of the following formats: Single Input, Multiple Inputs or JSON Lines (JSONL). For a complete sample for each of the accepted formats, see the documentation here

    Input MIME type
    application/json, application/jsonlines
    Sample input data
    Expand all input descriptions
    Field name
    input_text
    Description
    Provide a string for a single text or a list of strings for multiple inputs. Additionally, you can provide a dictionary or a list of dictionaries with keys "context" and "question" with "open_book_qa", and the input will be formatted accordingly before sending to the model. If no template is selected, the "context" and "question" strings will be concatenated with a newline.
    Required
    Yes
    Data type
    FreeText
    Field name
    max_tokens
    Description
    The maximum number of tokens the model should generate as output.
    Required
    No
    Data type
    Integer
    Range
    Min: 0
    Default value
    1024
    Field name
    temperature
    Description
    The temperature parameter controlling the randomness of token generation.
    Required
    No
    Data type
    Continuous (Float)
    Range
    Min: 0
    Default value
    0.7
    Field name
    repetition_penalty
    Description
    Penalizes new tokens based on whether they appear in the prompt and generated text so far. Values > 1 discourage repetition, while values < 1 encourage it.
    Required
    No
    Data type
    Continuous (Float)
    Range
    Min: 0
    Max: 2
    Default value
    1.2
    Field name
    top_p
    Description
    Controls nucleus sampling by selecting tokens with a cumulative probability of top_p.
    Required
    No
    Data type
    Continuous (Float)
    Range
    Min: 0
    Max: 1
    Default value
    0.9
    Field name
    top_k
    Description
    Limits the token selection to the top_k most likely tokens. Constraints: Must be -1 (disable) or a positive integer.
    Required
    No
    Data type
    Integer
    Range
    Default value
    50
    Field name
    template
    Description
    Specifies the predefined template to apply to the input text. Templates Available: { "summarization": "Summarize the following document:\n## Document Start ##\n{context}\n## Document End ##", "open_book_qa": "Answer the following question based on the given context:\n## Context Start ##\n{context}\n## Context End ##\n## Question Start ##\n{question}\n## Question End ##", "closed_book_qa": "Answer the following question:\n## Question Start ##\n{question}\n## Question End ##" }
    Required
    No
    Data type
    FreeText
    Default value
    None

    Output

    Summary

    The output is a JSON object or a set of JSON Lines objects that contain the generated text(s)

    JSON Format { "response": [ "model response for input 1", "model response for input 2", ... ] } JSON Lines (JSONL) Format {"response": "model response for input 1"} {"response": "model response for input 2"}

    The JSON Lines format consists of separate JSON objects, where each object represents a model response for the respective input.

    Output MIME type
    application/json, application/jsonlines
    Sample output data
    Expand all output descriptions
    Field name
    response
    Description
    JSON Format { "response": [ "model response for input 1", "model response for input 2", ... ] Each element within the "response" array corresponds to a model response for the respective input. } JSON Lines (JSONL) Format {"response": "model response for input 1"} {"response": "model response for input 2"} The JSON Lines format consists of separate JSON objects, where each object represents a model response for the respective input.
    Always returned
    Yes
    Data type
    FreeText

    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

    Medical LLM - 24B

    For any assistance, please reach out to support@johnsnowlabs.com.

    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 are possible.

    Customer Reviews

    There are currently no reviews for this product.
    View all