wiedersehne/Paramixer
Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention (CVPR 2022)
This project offers a way to analyze long sequences of data, such as images, text, or genomic sequences, to classify them or identify patterns more efficiently. It takes raw data like image files, text documents, or DNA sequences as input and outputs classifications or insights. This tool is designed for researchers, data scientists, or practitioners working with large datasets in fields like computer vision, natural language processing, or bioinformatics who need to process long sequences.
No commits in the last 6 months.
Use this if you are working with very long data sequences (e.g., in image recognition, document classification, or genomics) and need an efficient way to extract information or classify them.
Not ideal if your data sequences are short or if you don't have programming experience, as it requires setting up a Python environment and running scripts.
Stars
20
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/wiedersehne/Paramixer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
jadore801120/attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
bhavnicksm/vanilla-transformer-jax
JAX/Flax implimentation of 'Attention Is All You Need' by Vaswani et al....
kyegomez/SparseAttention
Pytorch Implementation of the sparse attention from the paper: "Generating Long Sequences with...
AbdelStark/attnres
Rust implementation of Attention Residuals from MoonshotAI/Kimi