Usually you have to write your own inference code. Default
predict_fn function is just returning a model. You may want to check the documentation here: https://docs.aws.amazon.com/sagemaker/latest/dg/adapt-inference-container.html
How to debug invocation timeout in sagemaker?asked 8 months ago
How to serve a model in sagemaker?asked 9 months ago
how to inference parameters to a huggingface model hosted in sagemaker?
Why does my kernal keep dying when I try to import Hugging Face BERT models to Amazon SageMaker?Accepted AnswerEXPERTasked 2 years ago
Visualizing custom Model Monitor metrics in Sagemaker Studioasked 7 months ago
Error: Sagemaker Lab for Hugging Face Exampleasked 7 months ago
Why does my kernel keep restarting when I try to download pre-trained Hugging Face BERT models weights to Amazon SageMaker?asked 5 months ago
How to serve a pretrained model from hugging face in sagemaker without custom script?
How to use custom functions for a model in a Sagemaker pipeline?asked 2 months ago
Incremental training with custom keras code in script modeasked 3 years ago