Intel
/

bert-base-uncased-sparse-80-1x4-block-pruneofa

Model card Files Files and versions

80% 1x4 Block Sparse BERT-Base (uncased) Prune OFA

This model is was created using Prune OFA method described in Prune Once for All: Sparse Pre-Trained Language Models presented in ENLSP NeurIPS Workshop 2021.

For further details on the model and its result, see our paper and our implementation available here.

Downloads last month: 15

Datasets used to train Intel/bert-base-uncased-sparse-80-1x4-block-pruneofa

Collection including Intel/bert-base-uncased-sparse-80-1x4-block-pruneofa

BERT

BERT models of varying flavors • 22 items • Updated 30 days ago

Paper for Intel/bert-base-uncased-sparse-80-1x4-block-pruneofa

Prune Once for All: Sparse Pre-Trained Language Models

Paper • 2111.05754 • Published Nov 10, 2021 • 2