No project description provided
Project description
Multibackend GLU and its variants
A Keras 3 port of Gated Linear Units and its variants. Ported from Rishit Dagli's Implementation
Installation
pip install glu_keras --upgrade
Usage
import keras
from glu_keras import SwiGLU
model = keras.Sequential()
model.add(keras.layers.Dense(units=10))
model.add(SwiGLU(bias = False, dim=-1, name='swiglu'))
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
glu_keras-0.0.2.tar.gz
(2.0 kB
view hashes)
Built Distribution
Close
Hashes for glu_keras-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 379c5c97902f04067083ccb364796041ccc99b6cee86d72811dcc3db78c08ab3 |
|
MD5 | 66b5a43c66cc91b89455127add48a3c0 |
|
BLAKE2b-256 | 228d95008d1462ee508fdd08206ebd207e13abdea268a52ba76bade83421ea69 |