{"id":13935708,"url":"https://github.com/prajjwal1/fluence","last_synced_at":"2025-06-12T03:08:18.393Z","repository":{"id":57431498,"uuid":"241266975","full_name":"prajjwal1/fluence","owner":"prajjwal1","description":"A deep learning library based on Pytorch focussed on low resource language research and robustness","archived":false,"fork":false,"pushed_at":"2021-11-30T22:45:01.000Z","size":3275,"stargazers_count":70,"open_issues_count":0,"forks_count":3,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-05-18T22:13:06.351Z","etag":null,"topics":["attention","deep-learning","nlp","pytorch","transformers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/prajjwal1.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-02-18T03:52:09.000Z","updated_at":"2025-04-21T17:05:08.000Z","dependencies_parsed_at":"2022-09-02T11:51:36.355Z","dependency_job_id":null,"html_url":"https://github.com/prajjwal1/fluence","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/prajjwal1/fluence","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prajjwal1%2Ffluence","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prajjwal1%2Ffluence/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prajjwal1%2Ffluence/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prajjwal1%2Ffluence/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/prajjwal1","download_url":"https://codeload.github.com/prajjwal1/fluence/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prajjwal1%2Ffluence/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259387616,"owners_count":22849747,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["attention","deep-learning","nlp","pytorch","transformers"],"created_at":"2024-08-07T23:02:00.992Z","updated_at":"2025-06-12T03:08:18.352Z","avatar_url":"https://github.com/prajjwal1.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/prajjwal1/fluence/master/docs/logo.png\" width=\"500\"\u003e\n\u003cbr /\u003e\n\u003cbr /\u003e\n\u003ca href=\"https://github.com/prajjwal1/fluence/releases\"\u003e\u003cimg alt=\"Latest Release\" src=\"https://img.shields.io/pypi/v/fluence\"/\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/prajjwal1/fluence/blob/master/LICENSE\"\u003e\u003cimg alt=\"Apache\" src=\"https://img.shields.io/github/license/prajjwal1/fluence\" /\u003e\u003c/a\u003e\n\u003ca href=\"https://codecov.io/gh/prajjwal1/fluence\"\u003e\u003cimg src=\"https://codecov.io/gh/prajjwal1/fluence/branch/master/graph/badge.svg\" /\u003e\u003c/a\u003e\n\nWinner of Pytorch Global Hackathon 2020.\n\nFluence 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.\n\n\u003cdetails\u003e\n\u003csummary\u003eList of implemented papers\u003c/summary\u003e\n\n#### Adaptive Methods\n- [Adaptive Attention Span in Transformers (ACL 2019)](https://arxiv.org/abs/1905.07799)\n- [Adaptively Sparse Transformers (EMNLP 2019)](https://arxiv.org/abs/1909.00015)\n- [Reducing Transformer Depth on Demand with Structured Dropout (ICLR 2020)](https://arxiv.org/abs/1909.11556)\n\n#### Debiasing\n- [Learning Robust Representations by Projecting Superficial Statistics Out (ICLR 2019)](https://openreview.net/pdf?id=rJEjjoR9K7)\n-------------------------------------------------------------------------------\n\n\u003c/details\u003e\n\n- [Installation](#installing)\n- [Overview](#overview)\n\n## Why Fluence ?\nFluence is targeted towards two main goals: \n1. **Compute efficiency**: Low resource research:\n2. **Robustness**: Algorithms that either enhance our understanding of current methods or show where SoTA methods fail.\n\nIt is as straightforward to use as [HF Transformers](https://github.com/huggingface/transformers), and fully integrates with [Pytorch](https://github.com/pytorch/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`.\n\n## Installing\nFor stable version:\n```bash\npip3 install --user fluence\n```\n\nFor development version (recommended):\n```bash\ngit clone https://github.com/prajjwal1/fluence\ncd fluence\npython3 setup.py install --user\n```\n\n## Overview\nThe library contains implementation for the following approaches (many more to come):   \n|  Module            |  Method with documentation\n| -------------------------------------------------------------------------------------- | ----------------------------\n| `fluence.adaptive` | [Adaptive Methods](https://github.com/prajjwal1/fluence/wiki/Adaptive-Methods)         |\n| `fluence.datasets` | [Datasets](https://github.com/prajjwal1/fluence/wiki/datasets)                         |      \n| `fluence.optim`    | [Optimizers](https://github.com/prajjwal1/fluence/wiki/Optimizers)                     |\n| `fluence.sampling` | [Importance Sampling](https://github.com/prajjwal1/fluence/wiki/Importance-sampling)   |\n| `fluence.models`   | [Siamese Methodology](https://github.com/prajjwal1/fluence/wiki/Siamese-Transformers), [Debiasing](https://github.com/prajjwal1/fluence/wiki/Debiasing)\n| `fluence.prune` | [Pruning](https://github.com/prajjwal1/fluence/wiki/Pruning)|\n\n## Documentation \nPlease head to this [link](https://github.com/prajjwal1/fluence/wiki) 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.\n\n### Contribution\nYou 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](https://github.com/prajjwal1/fluence/blob/master/CONTRIBUTING.md) for more details.\n\n\n### Tests\n\nFluence comes with an [extensive test suite](https://github.com/prajjwal1/fluence/tree/master/tests) for high test coverage.\n```\npytest tests/ -v\n```\n\nAuthor: Prajjwal Bhargava ([@prajjwal_1](https://twitter.com/prajjwal_1))\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprajjwal1%2Ffluence","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprajjwal1%2Ffluence","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprajjwal1%2Ffluence/lists"}