Effortlessly deploy Hugging Face models to production with ZenML
Integrate Hugging Face Inference Endpoints with ZenML to streamline the deployment of transformers, sentence-transformers, and diffusers models. This integration allows you to leverage Hugging Face's secure, scalable infrastructure for hosting models, while managing the deployment process within your ZenML pipelines.
from zenml.integrations.huggingface.steps import huggingface_model_deployer_step
from zenml.integrations.huggingface.services.huggingface_deployment import HuggingFaceDeploymentService
from zenml.integrations.huggingface.services import HuggingFaceServiceConfig
@step
def predictor(
service: HuggingFaceDeploymentService,
) -> Annotated[str, "predictions"]:
# Run a inference request against a prediction service
data = load_live_data()
prediction = service.predict(data)
return prediction
@pipeline
def deploy_and_infer():
service_config = HuggingFaceServiceConfig(model_name=model_name)
service = huggingface_model_deployer_step(
model_name="text-classification-model",
accelerator="gpu",
hf_repository="myorg/text-classifier",
task="text-classification"
)
predictor(service)
Expand your ML pipelines with more than 50 ZenML Integrations
