Batch_transform Pipeline?

Amazon SageMaker
6

I think the error is saying something different.
Could you try adding the accept parameter to

# create Transformer to run our batch job
batch_job = huggingface_model.transformer(
    instance_count=1,
    instance_type='ml.g4dn.xlarge',
    output_path=output_s3_path, # we are using the same s3 path to save the output with the input
    accept="application/json",
    strategy='SingleRecord')