Rishit-dagli/GLU
An easy-to-use library for GLU (Gated Linear Units) and GLU variants in TensorFlow.
This library provides various Gated Linear Units (GLU) activation functions, like GLU, SwiGLU, and GEGLU, for use within TensorFlow models. It takes your model's layers and applies these specific activation functions, helping improve performance on tasks like language understanding. This is for machine learning engineers and researchers building and training deep learning models.
No commits in the last 6 months.
Use this if you are developing deep learning models in TensorFlow and want to experiment with advanced GLU-based activation functions to potentially improve model accuracy and training efficiency.
Not ideal if you are not working with TensorFlow or are looking for a high-level, no-code solution for general machine learning tasks.
Stars
20
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Rishit-dagli/GLU"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ModelCloud/GPTQModel
LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD...
intel/auto-round
🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality...
pytorch/ao
PyTorch native quantization and sparsity for training and inference
bodaay/HuggingFaceModelDownloader
Simple go utility to download HuggingFace Models and Datasets
NVIDIA/kvpress
LLM KV cache compression made easy