https://github.com/lucidrains/light-recurrent-unit-pytorch
Implementation of a Light Recurrent Unit in Pytorch
https://github.com/lucidrains/light-recurrent-unit-pytorch
artificial-intelligence deep-learning recurrent-neural-networks
Last synced: 3 months ago
JSON representation
Implementation of a Light Recurrent Unit in Pytorch
- Host: GitHub
- URL: https://github.com/lucidrains/light-recurrent-unit-pytorch
- Owner: lucidrains
- License: mit
- Created: 2024-08-29T13:06:30.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-10-06T17:44:18.000Z (9 months ago)
- Last Synced: 2025-04-02T11:08:45.971Z (3 months ago)
- Topics: artificial-intelligence, deep-learning, recurrent-neural-networks
- Language: Python
- Homepage:
- Size: 35 MB
- Stars: 47
- Watchers: 1
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## Light Recurrent Unit - Pytorch
Implementation of the Light Recurrent Unit in Pytorch
## Install
```bash
$ pip install light-recurrent-unit-pytorch
```
## Usage
```python
import torch
from light_recurrent_unit_pytorch import LightRecurrentUnitCell
cell = LightRecurrentUnitCell(256)
x = torch.randn(2, 256)
hidden = torch.randn(2, 256)
next_hidden = cell(x, hidden) # (2, 256)
```
Single layer
```python
import torch
from light_recurrent_unit_pytorch import LightRecurrentUnitLayer
layer = LightRecurrentUnitLayer(256)
x = torch.randn(2, 1024, 256)
out = layer(x) # (2, 1024, 256)
assert out.shape == x.shape
```
Stacked
```python
import torch
from light_recurrent_unit_pytorch import LightRecurrentUnit
lru = LightRecurrentUnit(256, depth = 4)
x = torch.randn(2, 1024, 256)
out, layer_hiddens = lru(x) # (2, 1024, 256), List[(2, 256)]
assert out.shape == x.shape
```
## Test
Enwik8
```bash
$ python train.py
```
## Citations
```bibtex
@Article{electronics13163204,
AUTHOR = {Ye, Hong and Zhang, Yibing and Liu, Huizhou and Li, Xuannong and Chang, Jiaming and Zheng, Hui},
TITLE = {Light Recurrent Unit: Towards an Interpretable Recurrent Neural Network for Modeling Long-Range Dependency},
JOURNAL = {Electronics},
VOLUME = {13},
YEAR = {2024},
NUMBER = {16},
ARTICLE-NUMBER = {3204},
URL = {https://www.mdpi.com/2079-9292/13/16/3204},
ISSN = {2079-9292},
DOI = {10.3390/electronics13163204}
}
```
```bibtex
@article{Merrill2024TheIO,
title = {The Illusion of State in State-Space Models},
author = {William Merrill and Jackson Petty and Ashish Sabharwal},
journal = {ArXiv},
year = {2024},
volume = {abs/2404.08819},
url = {https://api.semanticscholar.org/CorpusID:269149086}
}
```