FAD-X: Fusioning Pretrained Adapters for Fast Adaptation to Low-Resource Languages

pip install -e .
pip install -r examples/pytorch/token-classification/requirements.txt

The code is based on adapter-transformers.

WikiAnn experiments

run following python files to generate sh files.

S(t) : submit_scripts/gen_wikiann.py. Must be ran before the followings (to generate TAs)
S(t) w/ param+ : submit_scripts/gen_wikiann_more_larger.py
Fuse(L), Fuse(L-LAt) : submit_scripts/gen_fused_wikiann.py
Fuse(L), Fuse(L-LAt) w/ ml (most resource-abundant) : submit_scripts/gen_fused_wikiann_ml.py

S(t) : submit_scripts/gen_amazon.py. Must be ran before the followings (to generate TAs)
Fuse(L), Fuse(L-LAt) : submit_scripts/gen_fused_amazon.py

Name		Name	Last commit message	Last commit date
Latest commit History 9,680 Commits
.github		.github
adapter_docs		adapter_docs
docker		docker
examples/pytorch		examples/pytorch
notebooks		notebooks
scripts		scripts
src/transformers		src/transformers
submit_scripts		submit_scripts
tests		tests
tests_adapters		tests_adapters
utils		utils
.gitattributes		.gitattributes
.gitignore		.gitignore
CITATION.cff		CITATION.cff
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
MANIFEST.in		MANIFEST.in
Makefile		Makefile
README.md		README.md
adding_adapters_to_a_model.md		adding_adapters_to_a_model.md
conftest.py		conftest.py
hubconf.py		hubconf.py
pyproject.toml		pyproject.toml
setup.cfg		setup.cfg
setup.py		setup.py
train_amazon.py		train_amazon.py
train_amazon_fusion.py		train_amazon_fusion.py