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':'Qwen/Qwen2.5-Omni-7B', 'HF_TASK':'any-to-any' } # create Hugging Face Model Class huggingface_model = HuggingFaceModel( transformers_version='4.49.0', pytorch_version='2.6.0', py_version='py312', 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 )

.gitattributes

@@ -30,3 +30,34 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
+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':'Qwen/Qwen2.5-Omni-7B',
+	'HF_TASK':'any-to-any'
+}
+
+# create Hugging Face Model Class
+huggingface_model = HuggingFaceModel(
+	transformers_version='4.49.0',
+	pytorch_version='2.6.0',
+	py_version='py312',
+	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
+)
+