Questions tagged with Amazon SageMaker Deployment
Content language: English
Select up to 5 tags to filter
Sort by most recent
Browse through the questions and answers listed below or filter and sort to narrow down your results.
Running into issues in getting Starcoder to deploy on Sagemaker.
I'm getting the following errors in CloudWatch and even with the instance type: ml.g5.8xlarge
Error 1:
```
Error: ShardCannotStart
...
2
answers
0
votes
299
views
asked 8 months agolg...
Is it possible (and efficient) to deploy an LLM model serverlessly using Sagemaker? I'm concerned about the performance and costs involved? The ML application doesn't receive a lot of requests.
2
answers
0
votes
1733
views
asked 9 months agolg...
I have been trying to deploy this HuggingFace model ( https://huggingface.co/bigcode/starcoderplus/tree/main ) to AWS Sagemaker but failed.
The error message from Cloudwatch is
> "No safetensors...
1
answers
0
votes
805
views
asked 9 months agolg...
I am encountering an issue while trying to calculate the AWS Signature for my requests. I have been following the AWS documentation and various examples, but I keep getting the following error:
"The...
2
answers
0
votes
694
views
asked 9 months agolg...
What type of instances can support models with 11B parameters ? I need to use this model for inference jobs.
1
answers
0
votes
139
views
asked 9 months agolg...
I need some clarification related to hyperparameters :
a) Ways to evaluate best hyperparameters result and how those are linked with model
b) Ways to version control parameters for training jobs
Accepted AnswerAmazon SageMaker Deployment
2
answers
0
votes
155
views
asked 9 months agolg...
I have a machine learning classification model that was trained outside of SageMaker. The model is in Scikit-learn format. To run this model, the preprocessing step requires the binary content of a...
2
answers
0
votes
360
views
asked 9 months agolg...
I am setting up autoscaling for a realtime inference endpoint in sagemaker. I set up a load test using locust, and by setting relatively high numbers (i.e: 100 users, with 10 user spawned per seconds)...
1
answers
0
votes
596
views
asked 10 months agolg...
Hi team !
I need to deploy a ton of Machine Learning Models (Timeseries models) and I'm seeking a way that is effective.
In details, the problem is to build a platform capable of serving many time...
1
answers
0
votes
544
views
asked 10 months agolg...
I am able to train and tune the model. But at the time of model deployment, the endpoint is not getting created, and it fails after some time. It gives the error as "FileNotFoundError: [Errno 2] No...
1
answers
0
votes
210
views
asked 10 months agolg...
i have a async inference on SageMaker, with BYOC. The job may take about 20 minutes and more. And i already set InvocationTimeoutSeconds to 3600 seconds.
the problem is, when i start a new...
1
answers
0
votes
236
views
asked 10 months agolg...
I am working on a project related to serverless inference API. Getting error while calling the CreateEndpoint API, need some reference or sample code related to serverless inference ?
Accepted AnswerAmazon SageMaker Deployment
1
answers
0
votes
229
views
asked 10 months agolg...