Questions tagged with Machine Learning & AI
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.
I've build a document based chatbot with sagemaker llama 2-7b model with Kendra index which is giving the answer but at the end it is adding 'don't know'.
but using same sagemaker model with faiss it...
0
answers
0
votes
293
views
asked 5 months agolg...
I have been working on a data extraction task using the Titan Lite model. I've noticed repeated instances where redaction appears to be applied to the response automatically. This makes the model...
1
answers
0
votes
575
views
asked 5 months agolg...
We have created a SageMaker Endpoint to deploy 2 PyTorch models and invoke them. Endpoint is created successfully and it is Real-Time. We receive error when we invoke this endpoint. The errors include...
1
answers
0
votes
697
views
asked 5 months agolg...
I have some questions regarding async inference of sagemaker model packages on aws marketplace
1. When packaging a model as a sagemaker model package to be offered on marketplace, can it support...
0
answers
0
votes
394
views
asked 5 months agolg...
Someone should add in some notes on the documentation stating that there you should be using relative file paths and using the document prefix, the fact that you can literally put the bucket as the...
1
answers
0
votes
471
views
asked 5 months agolg...
Hi, I have been analyzing the different options I have for running LLMs at the AWS cloud. I have seen in the console that I have available Claude Instant 1.2, Claude 2.1, 2 and 1.3.
Unfortunately,...
2
answers
0
votes
1056
views
asked 5 months agolg...
My company restricts the internet access for our sagemaker notebooks using VPC. I want to install some time series related packages to my conda environment in my notebooks at startup. So far I have...
3
answers
0
votes
640
views
asked 5 months agolg...
I am trying to deploy a proof-of-concept application using text-to-text LLM for a document knowledge repository. Every time I try to deploy a Sagemaker Jumpstart model I get some sort of a...
1
answers
0
votes
1647
views
asked 5 months agolg...
As per best practice to choose distance metric "Use the distance metric that matches the model that you're using". For Titan embedding model which distance metric to use.
Accepted AnswerMachine Learning & AI
2
answers
0
votes
492
views
asked 5 months agolg...
I'm deploying a custom inference.py on a neural network trained on Sagemaker and stored in S3. One issue is writing the inference.py and debugging as I am creating the endpoint. Each time, I have to...
1
answers
0
votes
202
views
asked 5 months agolg...
I am trying to create a model for DeepRacer for the first time, but every time I do, the error, "Failed to create model: User's country of residence" shows up. There was never an input for a country,...
1
answers
0
votes
292
views
asked 6 months agolg...
Pasting the blurb from this link - https://docs.aws.amazon.com/personalize/latest/dg/personalize-opensearch.html
"Continuing with this example, if a user searches for a specific type of car from a...
0
answers
0
votes
235
views
asked 6 months agolg...