Sagemaker endpoint inferencing error with HF model loading from s3bucket with new transformer update

Since the transformer update (4.35.0). model outputs model.safetensor by default instead of pytorch.bin

endpoint created in sagamaker with model saved in s3bucket is throwing error. asking to define `"HF_TASK"`.

As per documentation of toolkit we do not need to define env variables when loading model from s3 Bucket, just a customer inference.py is needed.

Does someone know what's going wrong here ? @philschmid any idea ?

Start by reproducing the SageMaker endpoint setup with the model saved in the S3 bucket, using the customer inference.py mentioned in the report and the transformer 4.35.0 model output. Compare the toolkit documentation's S3-loading behavior with the endpoint error requesting HF_TASK; done means identifying and documenting the compatibility or configuration issue.

Written by the indexing model from the issue text.