Select a branch to explore...
Based on this O'Reilly book:
In this hands-on workshop, we will build an end-to-end AI/ML pipeline to fine tune, evaluate, and deploy a state-of-the-art large language model (LLM) using with Amazon SageMaker and the Amazon Customer Reviews Dataset which contains 150+ million customer reviews from Amazon.com for the 20 year period between 1995 and 2015. In particular, we will fine-tune the large language model on the review_body column - as well as other columns depending on the language task.
Attendees will learn how to do the following:
- Ingest data into S3 using Amazon Athena, AWS Glue, Spark, Ray and the Parquet data format
- Visualize data with pandas, matplotlib on SageMaker notebooks
- Perform feature engineering on a raw dataset using Scikit-Learn, PySpark, and SageMaker Processing Jobs
- Store and share features using SageMaker Feature Store
- Fine-tune and evaluate a generative AI model using PyTorch and SageMaker Training Jobs
- Evaluate the model using SageMaker Processing Jobs
- Register and version models using SageMaker Model Registry
- Deploy a model to a REST endpoint using SageMaker Hosting and SageMaker Endpoints
- Automate ML workflow steps by building end-to-end model pipelines
Note: This workshop will create an ephemeral AWS acccount for each attendee. This ephemeral account is not accessible after the workshop. You can, of course, clone this GitHub repo and reproduce the entire workshop in your own AWS Account.
If you do not logout of existing AWS Consoles, things will not work properly.
Please logout of all AWS Console sessions in all browser tabs.
Take the defaults and click on Open AWS Console. This will open AWS Console in a new browser tab.
If you see this message, you need to logout from any previously used AWS accounts.
Please logout of all AWS Console sessions in all browser tabs.
Double-check that your account name is similar to TeamRole/MasterKey as follows:
If not, please logout of your AWS Console in all browser tabs and re-run the steps above!
Open the AWS Management Console
In the AWS Console search bar, type SageMaker and select Amazon SageMaker to open the service console.
Click File > New > Terminal to launch a terminal in your Jupyter instance.
Within the Terminal, run the following:
cd ~ && git clone -b generative https://github.com/data-science-on-aws/data-science-on-aws
If you see an error like the following, just re-run the command again until it works:
fatal: Unable to create '.git/index.lock': File exists.
Another git process seems to be running in this repository, e.g.
an editor opened by 'git commit'. Please make sure all processes
are terminated then try again. If it still fails, a git process
may have crashed in this repository earlier:
remove the file manually to continue.
Note: This is not a fatal error ^^ above ^^. Just re-run the command again until it works.
Navigate to the data-science-on-aws/ directory and start the workshop!
You may need to refresh your browser if you don't see the notebooks.