minGRU
Project description
minGRU
Implementation of the proposed minGRU in Pytorch, only the log-space numerically stable version.
Install
$ pip install minGRU-pytorch
Usage
import torch
from minGRU_pytorch import minGRU
min_gru = minGRU(512)
x = torch.randn(2, 1024, 512)
out = min_gru(x)
assert x.shape == out.shape
Test
enwik8
$ python train.py
Citations
@inproceedings{Feng2024WereRA,
title = {Were RNNs All We Needed?},
author = {Leo Feng and Frederick Tung and Mohamed Osama Ahmed and Yoshua Bengio and Hossein Hajimirsadegh},
year = {2024},
url = {https://api.semanticscholar.org/CorpusID:273025630}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mingru_pytorch-0.0.8.tar.gz
(36.6 MB
view details)
Built Distribution
File details
Details for the file mingru_pytorch-0.0.8.tar.gz
.
File metadata
- Download URL: mingru_pytorch-0.0.8.tar.gz
- Upload date:
- Size: 36.6 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 97fec7682309bcadb8542d35f2fe1e4cf5e6eee0d43105668adf2c11639cbbd2 |
|
MD5 | 2385bf3e98adc30bb0c16e6324dcaefc |
|
BLAKE2b-256 | 0202164dfda1c3de0a9da583e17936a93d08021d302ea1a4853a1e49333f74fd |
File details
Details for the file mingru_pytorch-0.0.8-py3-none-any.whl
.
File metadata
- Download URL: mingru_pytorch-0.0.8-py3-none-any.whl
- Upload date:
- Size: 5.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 32517141905b7d8e50468bfb783dfa49b49c24e795fd017a02bb8340ab259c95 |
|
MD5 | c8abb69877f4addef1c7fd0c892c0dce |
|
BLAKE2b-256 | 8ea3b898004536b2a8788e258a7c62db81c42488ec98dea4f213f572584bd1d5 |