IDSIA/lmtool-fwp

PyTorch Language Modeling Toolkit for Fast Weight Programmers

39
/ 100
Emerging

This toolkit helps machine learning researchers rapidly prototype and experiment with different language modeling architectures, particularly those involving 'Fast Weight Programmers.' It takes text datasets and model configurations as input, allowing you to train and evaluate various Transformer models or explore novel 'Fast Weight Programmer' designs. It's designed for researchers focused on advancing the state-of-the-art in neural network architectures for natural language processing.

No commits in the last 6 months.

Use this if you are a machine learning researcher developing new language models or exploring variations of Transformer architectures, especially those based on 'Fast Weight Programmers' and linear attention mechanisms.

Not ideal if you are a practitioner looking for an out-of-the-box solution for common NLP tasks like text classification or sentiment analysis, or if you require robust multi-GPU training with the latest PyTorch DistributedDataParallel.

natural-language-processing neural-network-research language-model-development deep-learning-experimentation transformer-architectures
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

19

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IDSIA/lmtool-fwp"

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