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-0.0.6.tar.gz
(36.6 MB
view details)
Built Distribution
File details
Details for the file mingru_pytorch-0.0.6.tar.gz
.
File metadata
- Download URL: mingru_pytorch-0.0.6.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 | 22b8d84ae1c91eead084da272b888de26f21e7d590a4cc32f2ff23cd24b20a2b |
|
MD5 | 7eab051cb01903a42e99d3baf06b4c96 |
|
BLAKE2b-256 | eb6087be24229781ce001bf8832896bcf024e95d02aa683585341594195b8ad5 |
File details
Details for the file mingru_pytorch-0.0.6-py3-none-any.whl
.
File metadata
- Download URL: mingru_pytorch-0.0.6-py3-none-any.whl
- Upload date:
- Size: 5.0 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 | 58144daf88b6efeb1c58576d27b628f2fc56fe63956947601d47a82e67b3f2e8 |
|
MD5 | 88005ed3266ef14cb28dbba2b3ef9823 |
|
BLAKE2b-256 | 5221a97fd10fb254ae7eb73a9bb62f3244131c40f277f34711907bfaf6dd33ee |