SageMaker deploy not working: fails with error InternalServerException

#30
by tomredman - opened

Using the provided snippet for deployment with SageMaker, I'm getting the following error. Anybody have any insight on how to resolve?

-----!Traceback (most recent call last):
  File "/Users/titan/projects/tomi/research/suno/sage.py", line 32, in <module>
    predictor.predict({
  File "/Users/titan/projects/tomi/research/suno/env/lib/python3.11/site-packages/sagemaker/base_predictor.py", line 185, in predict
    response = self.sagemaker_session.sagemaker_runtime_client.invoke_endpoint(**request_args)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/titan/projects/tomi/research/suno/env/lib/python3.11/site-packages/botocore/client.py", line 535, in _api_call
    return self._make_api_call(operation_name, kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/titan/projects/tomi/research/suno/env/lib/python3.11/site-packages/botocore/client.py", line 980, in _make_api_call
    raise error_class(parsed_response, operation_name)
botocore.errorfactory.ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{
  "code": 400,
  "type": "InternalServerException",
  "message": "\u0027bark\u0027"
}
". See https://us-east-1.console.aws.amazon.com/cloudwatch/home?region=us-east-1#logEventViewer:group=/aws/sagemaker/Endpoints/huggingface-pytorch-inference-2023-09-28-18-20-36-815 in account 017512296561 for more information.

Unsupported HuggingFace Version.
For bark, we need at least 4.31 HuggingFace Version, but sagemaker supports only till 4.29

Any news on this issue?

Any news on this issue?

Update: Just test and i get the same error.

Sign up or log in to comment