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 )
b1965bb verified | *.7z filter=lfs diff=lfs merge=lfs -text | |
| *.arrow filter=lfs diff=lfs merge=lfs -text | |
| *.bin filter=lfs diff=lfs merge=lfs -text | |
| *.bz2 filter=lfs diff=lfs merge=lfs -text | |
| *.ftz filter=lfs diff=lfs merge=lfs -text | |
| *.gz filter=lfs diff=lfs merge=lfs -text | |
| *.h5 filter=lfs diff=lfs merge=lfs -text | |
| *.joblib filter=lfs diff=lfs merge=lfs -text | |
| *.lfs.* filter=lfs diff=lfs merge=lfs -text | |
| *.model filter=lfs diff=lfs merge=lfs -text | |
| *.msgpack filter=lfs diff=lfs merge=lfs -text | |
| *.npy filter=lfs diff=lfs merge=lfs -text | |
| *.npz filter=lfs diff=lfs merge=lfs -text | |
| *.onnx filter=lfs diff=lfs merge=lfs -text | |
| *.ot filter=lfs diff=lfs merge=lfs -text | |
| *.parquet filter=lfs diff=lfs merge=lfs -text | |
| *.pb filter=lfs diff=lfs merge=lfs -text | |
| *.pickle filter=lfs diff=lfs merge=lfs -text | |
| *.pkl filter=lfs diff=lfs merge=lfs -text | |
| *.pt filter=lfs diff=lfs merge=lfs -text | |
| *.pth filter=lfs diff=lfs merge=lfs -text | |
| *.rar filter=lfs diff=lfs merge=lfs -text | |
| saved_model/**/* filter=lfs diff=lfs merge=lfs -text | |
| *.tar.* filter=lfs diff=lfs merge=lfs -text | |
| *.tflite filter=lfs diff=lfs merge=lfs -text | |
| *.tgz filter=lfs diff=lfs merge=lfs -text | |
| *.wasm filter=lfs diff=lfs merge=lfs -text | |
| *.xz filter=lfs diff=lfs merge=lfs -text | |
| *.zip 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 | |
| ) | |