latest | popular

Filter by
How to Train Your Neural Net
Deep learning for various tasks in the domains of Computer Vision, Natural Language Processing, Time Series Forecasting using PyTorch 1.0+.
pytorch python deep-learning computer-vision
NLP for Developers: Shrinking Transformers | Rasa
In this video, Rasa Senior Developer Advocate Rachael will talk about different approaches to make transformer models smaller.
model-compression distillation pruning transformers
The Lottery Ticket Hypothesis: A Survey
Dive deeper into the lottery ticket hypothesis and review the literature after the original ICLR best paper award by Frankle & Carbin (2019).
lottery-ticket-hypothesis survey deep-learning article
A Survey of Methods for Model Compression in NLP
A look at model compression techniques applied on base model pre-training to reduce the computational cost of prediction.
model-compression pruning knowledge-distillation precision-reduction
How to make your network smaller and faster with the use of fastai library.
model-compression fastai knowledge-distillation sparsifying
Compression of Deep Learning Models for Text: A Survey
In this survey, we discuss six different types of methods for compression of such models to enable their deployment in real industry NLP projects.
pruning quantization knowledge-distillation parameter-sharing
PyTorch Pruning | How it's Made by Michela Paganini
In this talk, you will learn about pruning, why it's important and how to get started using PyTorch's Pruning (torch.nn.utils.prune).
pruning pytorch model-compression video
Movement Pruning: Adaptive Sparsity by Fine-Tuning
We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning.
pruning movement-pruning sparsity adaptive-sparsity
All The Ways You Can Compress BERT
In this post I’ll list and briefly taxonomize all the papers I’ve seen compressing BERT.
bert pruning weight-factorization compression
projects 1 - 10 of 14
Topic experts
Share a project
Share something you or the community has made with ML.