castorini / DeeBERT

Related projects: ⓘ

• pmichel31415 / are-16-heads-really-better-than-1
  Code for the paper "Are Sixteen Heads Really Better than One?"
  ☆165Updated 4 years ago
• IBM / PoWER-BERT
  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
• JetRunner / PABEE
  Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit".
  ☆63Updated 3 years ago
• txsun1997 / awesome-early-exiting
  A curated list of Early Exiting papers, benchmarks, and misc.
  ☆91Updated 10 months ago
• princeton-nlp / CoFiPruning
  [ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
  ☆188Updated last year
• LorrinWWW / SkipBERT
  Code associated with the paper **SkipBERT: Efficient Inference with Shallow Layer Skipping**, at ACL 2022
  ☆15Updated 2 years ago
• intersun / PKD-for-BERT-Model-Compression
  pytorch implementation for Patient Knowledge Distillation for BERT Model Compression
  ☆198Updated 5 years ago
• TobiasLee / Awesome-Efficient-PLM
  Must-read papers on improving efficiency for pre-trained language models.
  ☆100Updated last year
• asappresearch / revisit-bert-finetuning
  For the code release of our arXiv paper "Revisiting Few-sample BERT Fine-tuning" (https://arxiv.org/abs/2006.05987).
  ☆184Updated last year
• fastnlp / ElasticBERT
  A pre-trained model with multi-exit transformer architecture.
  ☆54Updated last year
• VITA-Group / BERT-Tickets
  [NeurIPS 2020] "The Lottery Ticket Hypothesis for Pre-trained BERT Networks", Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Ya…
  ☆137Updated 2 years ago
• kssteven418 / LTP
  [KDD'22] Learned Token Pruning for Transformers
  ☆91Updated last year
• mitchellgordon95 / bert-prune
  ☆17Updated 4 years ago
• clovaai / length-adaptive-transformer
  Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)
  ☆100Updated 3 years ago
• Sanyuan-Chen / RecAdam
  Code for the RecAdam paper: Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.
  ☆114Updated 3 years ago
• SimiaoZuo / MoEBERT
  This PyTorch package implements MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (NAACL 2022).
  ☆96Updated 2 years ago
• huggingface / block_movement_pruning
  Block Sparse movement pruning
  ☆77Updated 3 years ago
• sai-prasanna / bert-experiments
  ☆20Updated 3 years ago
• castorini / berxit
  ☆21Updated 3 years ago
• JetRunner / BERT-of-Theseus
  ⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).
  ☆310Updated last year
• lena-voita / the-story-of-heads
  This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, t…
  ☆296Updated 3 years ago
• RayeRen / multilingual-kd-pytorch
  ICLR2019, Multilingual Neural Machine Translation with Knowledge Distillation
  ☆70Updated 3 years ago
• WoosukKwon / retraining-free-pruning
  [NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers
  ☆160Updated last year
• gonglinyuan / StackingBERT
  Source code for "Efficient Training of BERT by Progressively Stacking"
  ☆111Updated 5 years ago
• allenai / sledgehammer
  ☆47Updated 4 years ago
• TsinghuaAI / CPM-1-Pretrain
  Pretrain CPM-1
  ☆50Updated 3 years ago
• robeld / ERNIE
  Open Source Neural Machine Translation in PyTorch
  ☆17Updated 5 years ago
• kssteven418 / I-BERT
  [ICML'21 Oral] I-BERT: Integer-only BERT Quantization
  ☆220Updated last year
• ChandlerGuan / Transkimmer
  Code for ACL2022 publication Transkimmer: Transformer Learns to Layer-wise Skim
  ☆21Updated 2 years ago
• lonePatient / electra_pytorch
  ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
  ☆91Updated 3 years ago