Choosing a Model and an Ecosystem

We thought that testing transformer models by downloading them would require machine and human resources. Also, we might have thought that if a platform didn’t have an online sandbox by this time, it would be a risk to go further because of the work to test a few examples.

However, sites such as Hugging Face download pretrained models automatically in real time. So, what should we do? Thanks to that, we can run Hugging Face models in Jupyter notebook without installing anything on the machine ourselves.

We can also test Hugging Face models online.

The idea is to analyze without having anything to “install.” “Nothing to install” in 2022 can mean:

• Running a transformer task online.

• Running a transformer on Jupyter notebook that seamlessly downloads a pretrained model for a task, which we can run in a few lines.

• Running a transformer through an API.

The definition of “install” has expanded over the past few years. The definition of “online” has also widened. We can consider using a few lines of code to run an API a meta-online test.

We will refer to “without installing,” and “online” in a broad sense in this section. The figure below shows how we should test models “online”: