def exp_normalize(x):
      b = x.max()
      y = np.exp(x - b)
      return y / y.sum()
    
    from transformers import AutoModelForSequenceClassification, AutoTokenizer

    tokenizer = AutoTokenizer.from_pretrained(model_path)
    model = AutoModelForSequenceClassification.from_pretrained(model_path)
    model.eval()

    pairs = [["나는 너를 싫어해", "나는 너를 사랑해"], \
             ["나는 너를 좋아해", "너에 대한 나의 감정은 사랑 일 수도 있어"]]

    with torch.no_grad():
        inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
        scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
        scores = exp_normalize(scores.numpy())
        print (f'first: {scores[0]}, second: {scores[1]}')

import sagemaker
import boto3
from sagemaker.huggingface import HuggingFaceModel

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':'Dongjin-kr/ko-reranker',
	'HF_TASK':'text-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.28.1',
	pytorch_version='2.0.0',
	py_version='py310',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.g5.large' # ec2 instance type
)

runtime_client = boto3.Session().client('sagemaker-runtime')
payload = json.dumps(
    {
        "inputs": [
            {"text": "나는 너를 싫어해", "text_pair": "나는 너를 사랑해"},
            {"text": "나는 너를 좋아해", "text_pair": "너에 대한 나의 감정은 사랑 일 수도 있어"}
        ]
    }
)

response = runtime_client.invoke_endpoint(
    EndpointName="<endpoint-name>",
    ContentType="application/json",
    Accept="application/json",
    Body=payload
)

## deserialization
out = json.loads(response['Body'].read().decode()) ## for json
print (f'Response: {out}')