IBM / PoWER-BERT
Method to improve inference time for BERT. This is an implementation of the paper titled "PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination" accepted in ICML 2020.
☆61Updated 2 years ago
Alternatives and similar repositories for PoWER-BERT:
Users that are interested in PoWER-BERT are comparing it to the libraries listed below
- Code for the paper "A Theoretical Analysis of the Repetition Problem in Text Generation" in AAAI 2021.☆52Updated 2 years ago
- [NeurIPS 2020] "The Lottery Ticket Hypothesis for Pre-trained BERT Networks", Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Ya…☆140Updated 3 years ago
- Code for EMNLP 2020 paper CoDIR☆41Updated 2 years ago
- Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit".☆65Updated 3 years ago
- Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)☆101Updated 4 years ago
- ☆47Updated 4 years ago
- Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"☆47Updated 2 years ago
- Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"☆46Updated 2 years ago
- Code for the paper "Are Sixteen Heads Really Better than One?"☆171Updated 4 years ago
- ☆32Updated 3 years ago
- DisCo Transformer for Non-autoregressive MT☆77Updated 2 years ago
- ☆22Updated 4 years ago
- ☆19Updated 4 years ago
- ☆44Updated 4 years ago
- ICLR2019, Multilingual Neural Machine Translation with Knowledge Distillation☆70Updated 4 years ago
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆72Updated 3 years ago
- ☆44Updated 3 years ago
- ☆28Updated 3 years ago
- Parameter Efficient Transfer Learning with Diff Pruning☆73Updated 4 years ago
- Code for NeurIPS2020 "Incorporating BERT into Parallel Sequence Decoding with Adapters"☆32Updated 2 years ago
- DEMix Layers for Modular Language Modeling☆53Updated 3 years ago
- Code for "Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation"☆13Updated 4 years ago
- Sequence-Level Mixed Sample Data Augmentation☆21Updated 4 years ago
- Source code for paper: Knowledge Inheritance for Pre-trained Language Models☆38Updated 2 years ago
- ☆41Updated 4 years ago
- Code to support the paper "Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets"☆66Updated 3 years ago
- ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhi…☆49Updated 3 years ago
- ☆44Updated 3 years ago
- Code for the ACL-2022 paper "StableMoE: Stable Routing Strategy for Mixture of Experts"☆45Updated 2 years ago
- Code for ACL 2023 paper titled "Lifting the Curse of Capacity Gap in Distilling Language Models"☆28Updated last year