This quickstart demonstrates how to build a text summarization application with a Transformer model from the Hugging Face Model Hub.
Perform the following steps to run this project.
-
Clone the repository:
git clone https://github.com/bentoml/quickstart.git cd quickstart
-
Install the required dependencies:
pip install -r requirements.txt
-
Download the Transformer model.
python download_model.py
-
Serve your model as an HTTP server. This starts a local server at http://0.0.0.0:3000, making your model accessible as a web service.
bentoml serve service:svc
-
Build your Bento. In the BentoML framework, a Bento is a deployable artifact that contains your application's source code, models, configurations, and dependencies.
bentoml build
After your Bento is ready, you can push your Bento to BentoCloud or containerize it with Docker and deploy it on a variety of platforms.
For more information, see this quickstart in the BentoML documentation.