maum-ai/pnlp-mixer

Unofficial PyTorch Implementation for pNLP-Mixer: an Efficient all-MLP Architecture for Language (https://arxiv.org/abs/2202.04350)

37
/ 100
Emerging

This project offers an alternative way to build language models for tasks like intent recognition or sentiment analysis. It takes in text data and, through a unique architecture, produces highly accurate predictions without needing the extensive computational power and pre-training typically required by other models. Data scientists and machine learning engineers working on natural language processing tasks would find this useful.

No commits in the last 6 months.

Use this if you need to develop performant natural language understanding models but are constrained by computational resources or wish to avoid lengthy pre-training.

Not ideal if you primarily work with existing transformer-based models and are not looking to experiment with novel, more efficient architectures.

natural-language-processing intent-recognition sentiment-analysis resource-efficient-ml machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

66

Forks

8

Language

Python

License

BSD-3-Clause

Last pushed

Mar 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/maum-ai/pnlp-mixer"

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