Views
No views yet
1from sagemaker.huggingface.model import HuggingFaceModel
2
3
4# create Hugging Face Model Class
5huggingface_model = HuggingFaceModel(
6 model_data=s3_model_uri, # path to your model and script
7 role=role, # iam role with permissions to create an Endpoint
8 transformers_version="4.12", # transformers version used
9 pytorch_version="1.9", # pytorch version used
10 py_version='py37', # python version used
11)
12
13# Let SageMaker know that we've already compiled the model via neuron-cc
14huggingface_model._is_compiled_model = True
15
16# deploy the endpoint endpoint
17predictor = huggingface_model.deploy(
18 initial_instance_count=1, # number of instances
19 instance_type="ml.inf1.xlarge" # AWS Inferentia Instance
20)