metadata
license: bigscience-bloom-rail-1.0
license: creativeml-openrail-m ---import json import sagemaker import boto3 from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
try: role = sagemaker.get_execution_role() except ValueError: iam = boto3.client('iam') role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
Hub Model configuration. https://huggingface.co/models
hub = { 'HF_MODEL_ID':'intfloat/multilingual-e5-small' }
create Hugging Face Model Class
huggingface_model = HuggingFaceModel( image_uri=get_huggingface_llm_image_uri("huggingface-tei",version="1.2.3"), env=hub, role=role, )
deploy model to SageMaker Inference
predictor = huggingface_model.deploy( initial_instance_count=1, instance_type="ml.g5.2xlarge", )
send request
predictor.predict({ "inputs": "My name is Clara and I am", })