myscience/x-lstm

Pytorch implementation of the xLSTM model by Beck et al. (2024)

32
/ 100
Emerging

This project provides an unofficial implementation of the xLSTM model, a modern alternative to Transformers and State-Space models for tasks involving sequential data like text. It allows researchers and practitioners to train and experiment with xLSTM for generating text, taking raw text as input and producing new, coherent text sequences. It's designed for machine learning researchers and AI practitioners exploring advanced recurrent neural network architectures.

183 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner interested in experimenting with cutting-edge Long Short-Term Memory architectures for natural language processing tasks, particularly text generation, and want a Pytorch-based implementation with multi-GPU training support.

Not ideal if you need a production-ready, highly optimized, and officially supported implementation of xLSTM, or if your primary focus is on immediate application rather than model exploration and understanding.

natural-language-processing large-language-models deep-learning-research text-generation recurrent-neural-networks
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

183

Forks

19

Language

Python

License

Last pushed

Aug 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/myscience/x-lstm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.