Skip to content

Add example notebook for SageMaker JumpStart #281

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 17, 2025

Conversation

shchur
Copy link
Contributor

@shchur shchur commented Feb 14, 2025

Issue #, if available:

Description of changes:

  • Add pointers to fev and JumpStart notebook in the README
  • Add notebook describing how to deploy Chronos with SageMaker JumpStart

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

Copy link
Contributor

@abdulfatir abdulfatir left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Notebook looks great! I only have the following comments:

Why are we putting a role here? Should we just say your-sagemaker-role like in the next cell?

model = JumpStartModel(
    model_id=model_id,
    role="arn:aws:iam::572445798620:role/service-role/AmazonSageMaker-ExecutionRole-20240717T173077",
    instance_type="ml.c5.2xlarge",
)

Should we also add a catalogue of available options for model_id?

@shchur
Copy link
Contributor Author

shchur commented Feb 17, 2025

@abdulfatir thanks for catching this, Fatir! The role ARN was included by accident. I've updated the notebook based on your feedback.

Copy link
Contributor

@abdulfatir abdulfatir left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we update the phrasing from

(Not recommended) Original Chronos models in sizes small, base and large can be accessed, e.g., as autogluon-forecasting-chronos-t5-small. Note that these models require a GPU to run, are much slower and don't support covariates. We recommend to use Chronos-Bolt models instead.

to

Original Chronos models in sizes small, base and large can be accessed, e.g., as autogluon-forecasting-chronos-t5-small. Note that these models require a GPU to run, are much slower and don't support covariates. Therefore, for most practical purposes we recommend using Chronos-Bolt models instead.

Copy link
Contributor

@abdulfatir abdulfatir left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you @shchur!

@shchur shchur merged commit a996ca7 into amazon-science:main Feb 17, 2025
6 checks passed
@shchur shchur deleted the add-jumpstart-notebook branch February 17, 2025 09:35
@nai-kon
Copy link

nai-kon commented Feb 19, 2025

14 Feb 2024 🚀 Chronos-Bolt is now available on Amazon SageMaker...

I thinks it is not 2024, but 2025.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants