Questions tagged with Amazon SageMaker
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.
```
llm = SagemakerEndpoint(
endpoint_name=endpoint_name,
region_name=region,
model_kwargs={"max_new_tokens": 700, "top_p": 0.9, "temperature": 0.6},
endpoint_kwargs={...
2
answers
0
votes
299
views
asked 4 months agolg...
Hi,
I have a sagemaker pipeline (training pipeline) which creates a new version of the ML model on a periodical basis with retraining and pushes that version to model registry inside a studio. I want...
1
answers
1
votes
280
views
asked 4 months agolg...
```
from langchain import LLMChain
from langchain import SagemakerEndpoint
from langchain.prompts import PromptTemplate
from langchain.llms.sagemaker_endpoint import LLMContentHandler
import os
import...
1
answers
0
votes
651
views
asked 4 months agolg...
Hi,
Currently I'm trying to change framework the model is prepared from Tensorflow to Pytorch.
The issue I encounter is long time of request decoding (request with JSON to dict) - it takes around 200...
1
answers
0
votes
142
views
asked 4 months agolg...
Hi, I checked my billing panel this morning to see a large bill for SageMaker, even though we have not been using it this month it is still considerably higher than last month.
I've checked the...
1
answers
0
votes
213
views
asked 4 months agolg...
We are trying to create a Serverless Endpoint at AWS for the Segment Anything (SAM) model. We pulled its image from Docker Hub...
2
answers
0
votes
284
views
asked 4 months agolg...
I was inferring the facebook/opt-350m trained on Dahoas/full-hh-rlhf datatset. But while inferring by asking the questions but the answers are having some garbage value included
Example:
Input query...
1
answers
0
votes
120
views
asked 4 months agolg...
Hey, my company wants to build an LLM using any base models available in Sagemaker/Bedrock. We want to be sure about this if we train a model of our own, then will our training data be sent to the...
1
answers
1
votes
269
views
asked 4 months agolg...
I followed the Here the CDK deployment of a GenAI model through SageMaker JumpStart -...
1
answers
0
votes
919
views
asked 4 months agolg...
I am trying to train Faster-RCNN model available on SageMaker JumpStart and wonder if it is possible to use Data Parallelization feature to finish the job faster as the size of training data is big? I...
1
answers
0
votes
2073
views
asked 4 months agolg...
I'm having some troubles with fine-tuning Mistral 7b on JumpStart.
This is the error:
```
ErrorMessage "raise ValueError(
ValueError: DeepSpeed Zero-3 is not compatible with...
0
answers
0
votes
353
views
asked 4 months agolg...
I am trying to run an athena query in a Sagemaker R Kernel notebook. The query uses an external UDF function. This query works on athena console but gives the following error in the...
1
answers
0
votes
164
views
asked 4 months agolg...