This model was created using the pruna library. Pruna is a model optimization framework built for developers, enabling you to deliver more efficient models with minimal implementation overhead.

First things first, you need to install the pruna library:

You can use the transformers library to load the model but this might not include all optimizations by default.

To ensure that all optimizations are applied, use the pruna library to load the model using the following code:

For inference, you can use the inference methods of the original model like shown in the original model card. Alternatively, you can visit the Pruna documentation for more information.

The compression configuration of the model is stored in the smash_config.json file, which describes the optimization methods that were applied to the model.