All Content tagged with Amazon SageMaker

Hi - could it be that there is a mistake in the prebuilt inference.py files of the Meta JumpStart models (at least I tried with 3.1 8bn instruct and 3.2 3bn instruct), that the response does not inclu...

What is the correct base GPU container image for SageMaker JupyterLab that I can build my container on? Is there an example dockerfile for building on top of the base image? I have tried options in [t...

Unable to create notebook instances ml.t2.xlarge - “ResourceLimitExceeded, Resource for this account has been exceeded. Please contact customer support for assistance.” But I have no instances running...

I'm trying to deploy a quantized llama 3.1 70b model, wrote a custom model_fn to read it from disk, but after several errors and investigation I noticed that the loading function **model_fn** is calle...

Hi, I am using Sagemaker TrainingJob and it fails when it tries to upload the mode artifact to a bucket that has objectlock enabled. It throws this error: ClientError: Artifact upload failed:Error 7:...

I deploy ML model on ml.m5.2xlarge instance to get real-time inference. The first 8 requests load concurrently, but with high latency, as the instance has 8 cores. But the latency gradually increases ...

I have a batch transform job which which i am trying to run in jupyternotebook in studio. below is the code.Problem is the entrypoint is not getting triggered. ``` import sagemaker from sagemaker.mod...

Hi, I am instantiating an SKLearn estimator like this: ``` estimator = SKLearn( entry_point='steps/training.py', role=sm_execution_role, image_uri=image_uri, instance_type=instance_ty...

Hello, I am trying to use a property from a tuning step into a condition: ``` cond_lte = ConditionLessThanOrEqualTo( left=JsonGet( step_name=step_tuning.name, s3_uri=Join( ...

 Dear AWS Support Team, I am working on a report and need guidance on designing an architecture diagram for a solution usin...

When I attempt to deploy a model to an endpoint with initial_instance_count=1, it works fine. Attempting to deploy the same model to an endpoint with initial_instance_count=2, however, always results ...