facebookresearch/fairseq

Add support for Pfeiffer adapters to fairseq models

Open

#5,143 opened on May 24, 2023

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (6,224 forks)batch import
enhancementhelp wantedneeds triage

Repository metrics

Stars
 (29,107 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

🚀 Feature Request

Are there any examples or implementation of Pfeiffer Adapters in fairseq models? I'm exploring efficient ways of finetuning model and wanted to include adapters in fairseq models. How can I add them to any model? If possible I'd like to add a standalone adapter module which anyone can add to any fairseq model. Is this possible? Can someone please guide me on this? Thank you!

Contributor guide

Research direction
Study existing adapter implementations in fairseq (e.g., LoRA), understand the model architecture, and design a standalone adapter module that can be added to any fairseq model. Look at the AdapterHub or HuggingFace adapters for reference.
Tech stack
python
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
GitPython
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40