JetRunner / PABEE
Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit".
☆64Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for PABEE
- Method to improve inference time for BERT. This is an implementation of the paper titled "PoWER-BERT: Accelerating BERT Inference via Pro…☆58Updated last year
- Code for EMNLP 2020 paper CoDIR☆41Updated 2 years ago
- This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.☆45Updated 2 years ago
- Code for the paper "A Theoretical Analysis of the Repetition Problem in Text Generation" in AAAI 2021.☆51Updated 2 years ago
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆71Updated 2 years ago
- ☆116Updated 2 years ago
- Implementation of Mixout with PyTorch☆74Updated last year
- Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"☆44Updated 2 years ago
- The source code for the Cutoff data augmentation approach proposed in this paper: "A Simple but Tough-to-Beat Data Augmentation Approach …☆62Updated 4 years ago
- ☆66Updated 3 years ago
- ☆63Updated 2 years ago
- Code and datasets for the EMNLP 2020 paper "Calibration of Pre-trained Transformers"☆57Updated last year
- Code for EMNLP'21 paper "Types of Out-of-Distribution Texts and How to Detect Them"☆25Updated 3 years ago
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆167Updated 2 years ago
- Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper☆51Updated last year
- Code for ACL 2021 paper: Accelerating BERT Inference for Sequence Labeling via Early-Exit☆28Updated 2 years ago
- Data and code for our paper "Exploring and Predicting Transferability across NLP Tasks", to appear at EMNLP 2020.☆48Updated 3 years ago
- EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering☆70Updated 2 years ago
- ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost☆39Updated last year
- A unified approach to explain conditional text generation models. Pytorch. The code of paper "Local Explanation of Dialogue Response Gene…☆18Updated 2 years ago
- [EMNLP'21] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.☆75Updated 2 years ago
- Code for ACL 2023 paper titled "Lifting the Curse of Capacity Gap in Distilling Language Models"☆28Updated last year
- Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization (ACL 2021)☆17Updated 3 years ago
- Source code for paper: Knowledge Inheritance for Pre-trained Language Models☆38Updated 2 years ago
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆31Updated 3 years ago
- This repository contains the code for "How many data points is a prompt worth?"☆49Updated 3 years ago
- TBC☆26Updated 2 years ago
- ☆47Updated 4 years ago
- Code for EMNLP 2021 paper: Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting☆17Updated 2 years ago
- Bootstrapped Unsupervised Sentence Representation Learning (ACL 2021)☆29Updated 2 years ago