-
ModelErrorTraceback (most recent call last)
in ()
1 request = json.dumps({ "input": "Keep frozen"})
----> 3 print(predictor.predict(request).decode('utf-8'))
/home/ec2-user/anaconda3/envs…
-
Hello,
Thank you for your amazing work. I had an issue while trying to train the model on 4 GPUs. The trace is as shown below. I however was able to train the model with one GPU.
Could you please h…
-
IHAC who is using the Jupyter Plugin in Sagemaker Studio. It is a great plugin, but in the documentation there is a gap for us that I wasn't able to easily figure out in the source code:
Is there a…
-
Hi @angelarw, @zhreshold
I was following the below notebook to inference sagemaker object detection ssd model locally. I get an error reporting that commons module does not exist when executing the…
-
**Describe the bug**
Not sure if this is a bug or an unsupported feature. We've trained a semantic segmentation model, using the built in sagemaker semantic segmentation algorithm, (FCN with resenet …
-
If the Notebook to be run/scheduled requires additional *.py files there is no way to pass those files in. The ask would be to be able to pass in either a notebook to `run-notebook {schedule, run} not…
-
Hi, thank you so much for releasing this great code base!
I noticed that your Laion blog says that the pre-training of OpenLM 1B/7B took place on 128 or 256 A100s. Therefore, I'm wondering if the c…
-
HI folks, great job on this project! One note - I had zero issues downloading the large 774M model and fine-tuning this on 16MB using an AWS GPU. This was the p3dn.24xlarge, available on a SageMaker t…
-
Previous link: https://github.com/aws/amazon-sagemaker-examples/blob/main/sagemaker-fundamentals/create-endpoint/create_endpoint.ipynb.
This file is missing in main branch now.
-
Hi @philschmid, I want to use this terraform, however, in my use case I need to deploy falcon40 as an async endpoint with a scaling policy based on the "HasBacklogWithoutCapacity" metric.
In the c…