By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post

Questions tagged with Amazon SageMaker JumpStart

Amazon SageMaker JumpStart helps you quickly and easily get started with machine learning. To make it easier to get started, SageMaker JumpStart provides a set of solutions for the most common use cases that can be deployed readily with just a few clicks. The solutions are fully customizable and showcase the use of AWS CloudFormation templates and reference architectures so you can accelerate your ML journey. Amazon SageMaker JumpStart also supports one-click deployment and fine-tuning of more than 150 popular open source models such as natural language processing, object detection, and image classification models.

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.

45 results

Why is SageMaker Jumpstart with the llama 3.2 11B Model Limi...

I am using Sagemaker Jumpstart with the llama 3.2 11B model, and I notices that the maximum input + output token length is limited to 4096 tokens. However, the documentationfor llama 3.2 mentions a co...
Accepted AnswerAmazon SageMakerMachine Learning & AIAmazon SageMaker JumpStart
1
answers
2
votes
32
views
Fadil
asked 10 days ago

Accurate Method for Calculating Token Consumption for AI Usa...

I’m working with an enterprise customer in the UAE who plans to deploy a LLM Model from SageMaker JumpStart as their corporate internal chatbot solution. They have a specific requirement for cost allo...
Amazon SageMakerMachine Learning & AIAWS BillingAmazon SageMaker JumpStart
2
answers
0
votes
59
views
AWS
rePost_koushald
asked a month ago

Issue accessing to S3 bucket in Jumpstart.

Hello everyone. I've got a trouble accesing the S3 bucket in the part "Enter training dataset". Seems that the service (Jumpstart job training) doesn't recognize el name because of some policy or pe...
Accepted AnswerAmazon SageMakerAmazon SageMaker JumpStartAmazon SageMaker Studio
2
answers
0
votes
84
views
Mike
asked a month ago

Async Inference for Meta JumpStart SageMaker Models not work...

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...
Amazon SageMakerAmazon SageMaker JumpStartAWS Cloud Development Kit (CDK)
1
answers
1
votes
115
views
Manu
asked 3 months ago

Parameter validation failed: Unknown parameter in PrimaryCon...

Describe the bug I'm trying to deploy meta-textgeneration-llama-codellama-7b jumpstart model endpoints using python. In sage-maker notebook code works fine. But deployed same code in app.py file givi...
Amazon SageMakerMachine Learning & AIAmazon SageMaker JumpStart
0
answers
0
votes
234
views
Makarand
asked 9 months ago

G5 Series VM allocation for AWS Sage Maker Jump Start

Hi, We need one of the g5 series VMs available in any region for AWS Sage Maker Jump Start, as we couldn't proceed further with our project without this VM allocation. Also, 1) Is there any Criteria ...
High Performance ComputeAWS Management ConsoleComputeAvailabilityAmazon SageMaker JumpStart
1
answers
0
votes
555
views
Nexgen
asked 9 months ago

SageMaker JumpStart Incremental Training

Is it possible to incrementally train a stable diffusion model on SageMaker JumpStart? I am having difficulty finding a solid answer?
Accepted AnswerAmazon SageMakerMachine Learning & AIAmazon SageMaker JumpStart
1
answers
1
votes
851
views
aws_user1234
asked 10 months ago

Multi Class Model Training - SageMaker Jumpstart Issue

I am using SageMaker JumpStart to try and train a stable diffusion model. I have tried hypertuning the parameters to a very specific degree but cant seem to provide prompts/ output that shows my class...
Accepted AnswerAmazon SageMakerMachine Learning & AIAmazon SageMaker Model TrainingAmazon SageMaker JumpStart
1
answers
0
votes
1.2K
views
aws_user1234
asked 10 months ago

Not all models displayed in SageMaker Jumpstart

Hello, I'm new to Sagemaker and have created a domain in the Europe region. I'd like to work with Mistral from Jump Start, but it doesn't appear in the Hugging Face hub. I have 216 models available, ...
Build & Train ML ModelsAmazon SageMakerAmazon SageMaker JumpStart
2
answers
0
votes
1.6K
views
Vivien P
asked a year ago

Mistral 7b Sagemaker Jumpstart fine tuning

I've been successfully fine tuning Mistral 7b using sagemaker jumpstart. Today I started getting the error when fine tuning of "ImportError: cannot import name 'insecure_hashlib' from 'huggingface_h...
Amazon SageMakerMachine Learning & AIAmazon SageMaker JumpStart
1
answers
0
votes
1.6K
views
Aadu
asked a year ago

SageMaker JumpStart question

Hello, I am new to Amazon SageMaker and trying to use Mistral 7B instruct model from JumpStart. I get this error message when I press Deploy: "Failed to deploy endpoint The account-level service li...
Amazon SageMakerMachine Learning & AIAWS Account ManagementService QuotasAmazon SageMaker JumpStart
1
answers
0
votes
1.7K
views
Abdalla
asked a year ago

Explain more about "finetunable" attribute on Jumpstart mode...

This doc https://docs.aws.amazon.com/sagemaker/latest/dg/jumpstart-fine-tune.html says only models with 'finetunable" can be finetuned. But I found that for mistral-7b, which is tagged as not "finetun...
Accepted AnswerAmazon SageMakerAmazon SageMaker JumpStart
3
answers
0
votes
2K
views
Spring
asked a year ago