Hugging Face models have easy one-click deployment via model catalog. Still, some models such as facebook/audiogen-medium, are not available on the Azure model catalog and do not have Deploy button on Hugging Face.
I followed these official tutorials for deploying custom models:
Deploy a model as an online endpoint
Deploy and score a machine learning model by using an online endpoint
but I could not find a tutorial to deploy other Hugging Face models on Azure ML using Azure Python sdk v2.
Since I’m using audiocraft package which lets me use the model like this:
from audiocraft.models import AudioGen
model = AudioGen.get_pretrained("facebook/audiogen-medium")
model.set_generation_params(duration=5) # generate 5 seconds.
descriptions = ['dog barking', 'sirene of an emergency vehicle', 'footsteps in a corridor']
wav = model.generate(descriptions) # generates 3 samples.
I have an error when I want to register the model, I don’t exactly know what should I use for the path attribute of the Model, the local path of the downloaded Hugging Face model?
model = Model(
name="audiogen",
version="1",
type=AssetTypes.CUSTOM_MODEL,
path="./score.py",
description="facebook/audiogen model for sound effects generation",
)
# Register the model
ml_client.models.create_or_update(model)
---> 10 ml_client.models.create_or_update(model)
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/_telemetry/activity.py:289, in monitor_with_activity.<locals>.monitor.<locals>.wrapper(*args, **kwargs)
285 with tracer.span():
286 with log_activity(
287 logger.package_logger, activity_name or f.__name__, activity_type, custom_dimensions
288 ):
--> 289 return f(*args, **kwargs)
290 elif hasattr(logger, "package_logger"):
291 with log_activity(logger.package_logger, activity_name or f.__name__, activity_type, custom_dimensions):
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/operations/_model_operations.py:158, in ModelOperations.create_or_update(self, model)
151 raise ValidationException(
152 message=msg,
153 no_personal_data_message=msg,
154 target=ErrorTarget.MODEL,
155 error_category=ErrorCategory.USER_ERROR,
156 )
157 if model.name is not None:
--> 158 model_properties = self._get_model_properties(model.name)
159 if model_properties is not None and _is_evaluator(model_properties) != _is_evaluator(model.properties):
160 if _is_evaluator(model.properties):
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/operations/_model_operations.py:815, in ModelOperations._get_model_properties(self, name, version, label)
813 if version or label:
814 return self.get(name, version, label).properties
--> 815 return self._get_latest_version(name).properties
816 except (ResourceNotFoundError, ValidationException):
817 return None
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/operations/_model_operations.py:620, in ModelOperations._get_latest_version(self, name)
615 def _get_latest_version(self, name: str) -> Model:
616 """Returns the latest version of the asset with the given name.
617
618 Latest is defined as the most recently created, not the most recently updated.
619 """
--> 620 result = _get_latest(
621 name,
622 self._model_versions_operation,
623 self._resource_group_name,
624 self._workspace_name,
625 self._registry_name,
626 )
627 return Model._from_rest_object(result)
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/_utils/_asset_utils.py:853, in _get_latest(asset_name, version_operation, resource_group_name, workspace_name, registry_name, order_by, **kwargs)
833 result = (
834 version_operation.list(
835 name=asset_name,
(...)
850 )
851 )
852 try:
--> 853 latest = result.next()
854 except StopIteration:
855 latest = None
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/core/paging.py:123, in ItemPaged.__next__(self)
121 if self._page_iterator is None:
122 self._page_iterator = itertools.chain.from_iterable(self.by_page())
--> 123 return next(self._page_iterator)
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/core/paging.py:75, in PageIterator.__next__(self)
73 raise StopIteration("End of paging")
74 try:
---> 75 self._response = self._get_next(self.continuation_token)
76 except AzureError as error:
77 if not error.continuation_token:
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/_restclient/v2023_08_01_preview/operations/_model_versions_operations.py:427, in ModelVersionsOperations.list.<locals>.get_next(next_link)
426 def get_next(next_link=None):
--> 427 request = prepare_request(next_link)
429 pipeline_response = self._client._pipeline.run( # pylint: disable=protected-access
430 request,
431 stream=False,
432 **kwargs
433 )
434 response = pipeline_response.http_response
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/_restclient/v2023_08_01_preview/operations/_model_versions_operations.py:371, in ModelVersionsOperations.list.<locals>.prepare_request(next_link)
368 def prepare_request(next_link=None):
369 if not next_link:
--> 371 request = build_list_request(
372 subscription_id=self._config.subscription_id,
373 resource_group_name=resource_group_name,
374 workspace_name=workspace_name,
375 name=name,
376 api_version=api_version,
377 skip=skip,
378 order_by=order_by,
379 top=top,
380 version=version,
381 description=description,
382 offset=offset,
383 tags=tags,
384 properties=properties,
385 feed=feed,
386 list_view_type=list_view_type,
387 stage=stage,
388 template_url=self.list.metadata['url'],
389 )
390 request = _convert_request(request)
391 request.url = self._client.format_url(request.url)
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/azure/ai/ml/_restclient/v2023_08_01_preview/operations/_model_versions_operations.py:63, in build_list_request(subscription_id, resource_group_name, workspace_name, name, **kwargs)
58 # Construct URL
59 _url = kwargs.pop("template_url", "/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/models/{name}/versions") # pylint: disable=line-too-long
60 path_format_arguments = {
61 "subscriptionId": _SERIALIZER.url("subscription_id", subscription_id, 'str', min_length=1),
62 "resourceGroupName": _SERIALIZER.url("resource_group_name", resource_group_name, 'str', max_length=90, min_length=1),
---> 63 "workspaceName": _SERIALIZER.url("workspace_name", workspace_name, 'str', pattern=r'^[a-zA-Z0-9][a-zA-Z0-9_-]{2,32}$'),
64 "name": _SERIALIZER.url("name", name, 'str'),
65 }
67 _url = _format_url_section(_url, **path_format_arguments)
69 # Construct parameters
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/msrest/serialization.py:652, in Serializer.url(self, name, data, data_type, **kwargs)
650 data = self._http_component_validation(data, data_type, name, **kwargs)
651 try:
--> 652 output = self.serialize_data(data, data_type, **kwargs)
653 if data_type == 'bool':
654 output = json.dumps(output)
File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/msrest/serialization.py:760, in Serializer.serialize_data(self, data, data_type, **kwargs)
749 """Serialize generic data according to supplied data type.
750
751 :param data: The data to be serialized.
(...)
757 :raises: SerializationError if serialization fails.
758 """
759 if data is None:
--> 760 raise ValueError("No value for given attribute")
762 try:
763 if data_type in self.basic_types.values():
ValueError: No value for given attribute
or just the score.py script which is necassary and is as follows (I used this for now and got the error above):
import json
import os
from audiocraft.models import AudioGen
from audiocraft.data.audio import audio_write
from azure.storage.blob import BlobServiceClient, BlobClient, ContainerClient
def init():
global model, blob_service_client, container_name
model = AudioGen.get_pretrained('facebook/audiogen-medium')
model.set_generation_params(duration=5)
# Initialize Azure Blob Storage client
connect_str = os.getenv('AZURE_STORAGE_CONNECTION_STRING')
blob_service_client = BlobServiceClient.from_connection_string(connect_str)
container_name = 'audiogen_generated_files'
def run(payload: str):
data = json.loads(payload)
theme = data["theme"]
prompts = [f'{theme}, slow speed', f'{theme}, fast speed', f'{theme} door closing', f'{theme} starting']
wavs = model.generate(prompts)
urls = []
for idx, one_wav in enumerate(wavs):
file_name = f'{theme}_{idx}.wav'
local_file_path = f'/tmp/{file_name}'
audio_write(local_file_path, one_wav.cpu(), model.sample_rate, strategy="loudness", loudness_compressor=True)
blob_client = blob_service_client.get_blob_client(container=container_name, blob=file_name)
with open(local_file_path, "rb") as data:
blob_client.upload_blob(data, overwrite=True)
urls.append(blob_client.url)
os.remove(local_file_path)
result = {"urls": urls}
return result
This is how I create the endpoint and deployment in the next steps:
endpoint = ManagedOnlineEndpoint(
name="audiogen-endpoint-" + str(uuid.uuid4())[:8],
description="audiogen inference endpoint",
auth_mode="key"
)
endpoint = ml_client.online_endpoints.begin_create_or_update(endpoint).result()
deployement = ManagedOnlineDeployment(
name="audiogen-deployment-mo",
endpoint_name=endpoint.name,
model=ml_client.models.get(name=model.name, version="1"),
instance_count=1,
)
deployement = ml_client.begin_create_or_update(deployement).result()
I want to know the proper way to deploy the model, also am I doing the other steps correcly?