Update app.py

app.py

@@ -1,31 +1,33 @@
-import sagemaker
-from sagemaker.huggingface import HuggingFace
+from sagemaker.huggingface import HuggingFaceModel
+import boto3
 
-# gets role for executing training job
-role = sagemaker.get_execution_role()
-hyperparameters = {
-	'model_name_or_path':'PygmalionAI/pygmalion-6b',
-	'output_dir':'/opt/ml/model'
-	# add your remaining hyperparameters
-	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/language-modeling
+iam_client = boto3.client('iam')
+role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
+# Hub Model configuration. https://huggingface.co/models
+hub = {
+	'HF_MODEL_ID':'PygmalionAI/pygmalion-6b',
+	'HF_TASK':'conversational'
 }
 
-# git configuration to download our fine-tuning script
-git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}
-
-# creates Hugging Face estimator
-huggingface_estimator = HuggingFace(
-	entry_point='run_clm.py',
-	source_dir='./examples/pytorch/language-modeling',
-	instance_type='ml.p3.2xlarge',
-	instance_count=1,
-	role=role,
-	git_config=git_config,
+# create Hugging Face Model Class
+huggingface_model = HuggingFaceModel(
 	transformers_version='4.17.0',
 	pytorch_version='1.10.2',
 	py_version='py38',
-	hyperparameters = hyperparameters
+	env=hub,
+	role=role, 
+)
+
+# deploy model to SageMaker Inference
+predictor = huggingface_model.deploy(
+	initial_instance_count=1, # number of instances
+	instance_type='ml.m5.xlarge' # ec2 instance type
 )
 
-# starting the train job
-huggingface_estimator.fit()
+predictor.predict({
+	'inputs': {
+		"past_user_inputs": ["Which movie is the best ?"],
+		"generated_responses": ["It's Die Hard for sure."],
+		"text": "Can you explain why ?"
+	}
+})