amazon-sagemaker-examples VS onnx

I need to use AWS Sagemaker (required, can't use easier services) and my adviser gave me this document to start with: https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/question_answering_langchain_jumpstart.ipynb

I'm trying to define a step scaling policy for my sagemaker realtime endpoint, based on this example notebook. I understand that the step scaling policy defines thresholds to provision a different amount of instances, but I am confused because it doesn't seem to specify the metrics to track.

Yeah man: https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_to_image/Amazon_JumpStart_Text_To_Image.ipynb

It's time to get your hands dirty by solving some ML Use Cases of your own from AWS SageMaker Use Cases repo.

Additionally, you can easily deploy pretrained fastText models on their own to live SageMaker endpoints to compute embedding vectors on the fly for use in relevant word-level tasks. See the following GitHub example for more details.

We are kind of boxed into using Sagemaker at our organization and we need to do a POC for Sagemaker's model monitoring. We noticed that Sagemaker monitoring works best with models that use tabular data/features. There are a lot of example notebooks that demonstrate model monitoring capabilities, but all of the examples are based on tabular data. We are trying to apply Sagemaker's model monitoring and gather metrics from Data Quality, Model Quality, Bias Drift, Feature Attribution Drift, and Explainability and then push those metrics into CloudWatch, similar to what was done in these notebooks: https://github.com/aws/amazon-sagemaker-examples/tree/main/sagemaker_model_monitor .

Amazon SageMaker provides XGBoost as a built-in algorithm and data science team decided to use it and re-train the model. So, data scientists just need to call built-in version and provide path to data on S3, more detailed description can be found in documentation. Example notebook can be found here.

Amazon SageMaker provides four new tabular data modeling algorithms: LightGBM, CatBoost, AutoGluon-Tabular and TabTransformer. These popular, state-of-the-art algorithms can be used for both tabular classification and regression tasks. They are available through the SageMaker JumpStart UI inside of SageMaker Studio, as well as through python code using SageMaker Python SDK. To learn how to use these algorithms, you can find SageMaker example notebooks below:

In this section, we go through an example in which we show you how to compile a BERT model with Neo for AWS Inferentia. We then deploy that model to a SageMaker endpoint. You can find a sample notebook describing the whole process in detail on GitHub.

Once your model has been trained and validated using Anomalib, the next step is to prepare it for real-time implementation. This is where ONNX (Open Neural Network Exchange) or OpenVINO (Open Visual Inference and Neural network Optimization) comes into play.

ONNX is an open format from the Linux Foundation to represent machine learning models. It is becoming extensively adopted by the Machine Learning community and is compatible with most of the machine learning frameworks like PyTorch, TensorFlow, etc. Converting a model between any of those formats and ONNX is really simple and can be done in most cases with a single command.

ONNX[0], model-as-protosbufs, continuing to gain adoption will hopefully solve this issue.

[0] https://github.com/onnx/onnx

Running inference for large models on CPU is not a new problem and fortunately there has been great development in many different optimization frameworks for speeding up matrix and tensor computations on CPU. We explored multiple optimization frameworks and methods to improve latency, namely TorchScript, BetterTransformer and ONNX.

ONNX is a format for representing machine learning models in a portable way. Additionally, ONNX models can be easily optimized and thus become smaller and faster.

I would say onnx.ai [0] provides more information about ONNX for those who aren’t working with ML/DL.

[0] https://onnx.ai

It's not clear why you thing this sub is appropriate for some third party system with a Python interface. Why don't you try their discussion group: https://github.com/onnx/onnx/discussions

This kind of indirection through standardisation is pretty common to make compatibility between different kinds of software components easier. Some other good examples are the LSP project from Microsoft and ONNX to represent machine learning models. The first provides a standard so that IDEs don't have to re-invent the weel for every programming language. The latter decouples training frameworks from inference frameworks. Going back to WSGI, you can find a pretty extensive rationale for the WSGI standard here if interested.