echarlaix/

bart-base-cnn-r2-18.7-d23-hybrid

This model was created using the nn_pruning python library: the linear layers contains 23% of the original weights.

The model contains 45% of the original weights overall (the embeddings account for a significant part of the model, and they are not pruned by this method).

This model was fine-tuned from the HuggingFace model. A side-effect of block pruning is that some of the attention heads are completely removed: 61 heads were removed on a total of 216 (28.2%).