Winner of Pytorch Global Hackathon 2020.

Fluence is a Pytorch based deep learning library focussed on providing computationally efficient, low resource methods and algorithms for NLP. Although the main focus is to provide support with transformers for NLP tasks, it can be extended with other domains and architectures as well. Currently in pre-alpha stage.

List of implemented papers

Adaptive Methods

• Adaptive Attention Span in Transformers (ACL 2019)
• Adaptively Sparse Transformers (EMNLP 2019)
• Reducing Transformer Depth on Demand with Structured Dropout (ICLR 2020)

Debiasing

• Learning Robust Representations by Projecting Superficial Statistics Out (ICLR 2019)

---

• Installation
• Overview

Why Fluence ?

Fluence is targeted towards two main goals:

1. Compute efficiency: Low resource research:
2. Robustness: Algorithms that either enhance our understanding of current methods or show where SoTA methods fail.

It is as straightforward to use as HF Transformers, and fully integrates with Pytorch. Please note that the current modules (meta-trainer, siamese-trainer) which rely on inherited Trainer works with transformers==3.0. Newer version comes with a modified Trainer.

Installing

For stable version:

pip3 install --user fluence

For development version (recommended):

git clone https://github.com/prajjwal1/fluence
cd fluence
python3 setup.py install --user

Overview

The library contains implementation for the following approaches (many more to come):

Module	Method with documentation
fluence.adaptive	Adaptive Methods
fluence.datasets	Datasets
fluence.optim	Optimizers
fluence.sampling	Importance Sampling
fluence.models	Siamese Methodology, Debiasing
fluence.prune	Pruning

Documentation

Please head to this link to learn how you can integrate fluence with your workflow. Since it's an early release, there might be bugs. Please file an issue if you encounter one. Docs are a work-in-progress.

Contribution

You can contribute by either filing an issue or sending a Pull Request (if you encounter any bug or want some features to be added). Please checkout the contributing guide for more details.

Tests

Fluence comes with an extensive test suite for high test coverage.

pytest tests/ -v

Author: Prajjwal Bhargava (@prajjwal_1)