Create deploy.py

deploy.py

@@ -0,0 +1,37 @@
+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':'oMarquess/trained-2k10-v4-model-merged',
+	'SM_NUM_GPUS': json.dumps(1)
+}
+
+
+
+# create Hugging Face Model Class
+huggingface_model = HuggingFaceModel(
+	image_uri=get_huggingface_llm_image_uri("huggingface",version="0.9.3"),
+	env=hub,
+	role=role, 
+)
+
+# deploy model to SageMaker Inference
+predictor = huggingface_model.deploy(
+	initial_instance_count=1,
+	instance_type="ml.g5.2xlarge",
+	container_startup_health_check_timeout=300,
+  )
+  
+# send request
+predictor.predict({
+	"inputs": "My name is Julien and I like to",
+})