Closed
Description
Instructions on https://github.com/aws/sagemaker-huggingface-inference-toolkit suggests the following:
# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
transformers_version='4.4',
pytorch_version='1.6',
env=hub,
role=role,
name=hub['HF_MODEL_ID'],
)
However it comes back with "The image '763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-inference:1.7.1-transformers4.4-gpu-py36-cu110-ubuntu18.04' does not exist.."
I found this blog that references a different transformer and pytorch version:
https://aws.amazon.com/blogs/machine-learning/announcing-managed-inference-for-hugging-face-models-in-amazon-sagemaker/
# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
model_data="s3://bucket/model.tar.gz", # S3 path to your trained sagemaker model
role=<SageMaker Role>, # IAM role with permissions to create an Endpoint
transformers_version="4.6", # transformers version used
pytorch_version="1.7", # pytorch version used
py_version="py36", # python version of the DLC
)
Could you update this repo to prevent further confusion?
Metadata
Metadata
Assignees
Labels
No labels