Sparsegpt: Massive language models can be accurately pruned in one-shot
E Frantar, D Alistarh - International Conference on Machine …, 2023 - proceedings.mlr.press
We show for the first time that large-scale generative pretrained transformer (GPT) family
models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal …
models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal …
Gptq: Accurate post-training quantization for generative pre-trained transformers
Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart
through breakthrough performance across complex language modelling tasks, but also by …
through breakthrough performance across complex language modelling tasks, but also by …
A simple and effective pruning approach for large language models
As their size increases, Large Languages Models (LLMs) are natural candidates for network
pruning methods: approaches that drop a subset of network weights while striving to …
pruning methods: approaches that drop a subset of network weights while striving to …
Optimal brain compression: A framework for accurate post-training quantization and pruning
E Frantar, D Alistarh - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We consider the problem of model compression for deep neural networks (DNNs) in the
challenging one-shot/post-training setting, in which we are given an accurate trained model …
challenging one-shot/post-training setting, in which we are given an accurate trained model …
Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks
The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …
reduce the size of neural networks by selectively pruning components. Similarly to their …
OPTQ: Accurate quantization for generative pre-trained transformers
Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart
through breakthrough performance across complex language modelling tasks, but also by …
through breakthrough performance across complex language modelling tasks, but also by …
Fishr: Invariant gradient variances for out-of-distribution generalization
Learning robust models that generalize well under changes in the data distribution is critical
for real-world applications. To this end, there has been a growing surge of interest to learn …
for real-world applications. To this end, there has been a growing surge of interest to learn …
Training neural networks with fixed sparse masks
During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …
parameters are updated at each iteration. Recent work has shown that it is possible to …
Group fisher pruning for practical network compression
Network compression has been widely studied since it is able to reduce the memory and
computation cost during inference. However, previous methods seldom deal with …
computation cost during inference. However, previous methods seldom deal with …
The optimal bert surgeon: Scalable and accurate second-order pruning for large language models
Transformer-based language models have become a key building block for natural
language processing. While these models are extremely accurate, they can be too large and …
language processing. While these models are extremely accurate, they can be too large and …