Block pruning for faster transformers F Lagunas, E Charlaix, V Sanh, AM Rush arXiv preprint arXiv:2109.04838, 2021 | 156 | 2021 |
Fully quantized transformer for machine translation G Prato, E Charlaix, M Rezagholizadeh arXiv preprint arXiv:1910.10485, 2019 | 70 | 2019 |
Fully quantized transformer for improved translation G Prato, E Charlaix, M Rezagholizadeh | 26 | 2019 |
Kroneckerbert: Learning kronecker decomposition for pre-trained language models via knowledge distillation MS Tahaei, E Charlaix, VP Nia, A Ghodsi, M Rezagholizadeh arXiv preprint arXiv:2109.06243, 2021 | 17 | 2021 |
KroneckerBERT: Significant compression of pre-trained language models through kronecker decomposition and knowledge distillation M Tahaei, E Charlaix, V Nia, A Ghodsi, M Rezagholizadeh Proceedings of the 2022 Conference of the North American Chapter of the …, 2022 | 9 | 2022 |
Method and system for smooth training of a quantized neural network E Charlaix, V Courville, VP NIA US Patent App. 17/701,257, 2023 | 1 | 2023 |