.dvcignore
.gitignore
.gitlab-ci.yml
.pre-commit-config.yaml
.pylintrc
LICENSE
README.md
codecov.yml
commitlint.config.js
dvc.lock
dvc.yaml
params.yaml
pyproject.toml
requirements-dev.txt
requirements.txt
setup.cfg
tox.ini
.dvc/.gitignore
codcat/__init__.py
codcat/cli.py
codcat/downloader.py
codcat/manifest.yaml
codcat/pyg.py
codcat/tok.py
codcat.egg-info/PKG-INFO
codcat.egg-info/SOURCES.txt
codcat.egg-info/dependency_links.txt
codcat.egg-info/requires.txt
codcat.egg-info/top_level.txt
codcat/models/__init__.py
codcat/models/estimator.py
codcat/utils/__init__.py
codcat/utils/dataset.py
codcat/utils/tokenization.py
codcat/utils/types.py
comparisons/__init__.py
comparisons/nn.py
comparisons/requirements.txt
comparisons/tools.py
comparisons/train.py
comparisons/docker/Dockerfile
comparisons/docker/docker-compose.yml
comparisons/docker/nginx.conf
data/.gitignore
data/code-snippets.csv.dvc
eval/live/metrics.json
notebooks/1-eda.ipynb
notebooks/2-preprocessing.ipynb
notebooks/3-bagofwords-tfidf.ipynb
notebooks/4-embeddings.ipynb
notebooks/5-sentence-transformers.ipynb
notebooks/6-code25-dataset.ipynb
notebooks/7-code-tokenize.ipynb
notebooks/8-final-evaluations.ipynb
notebooks/__init__.py
notebooks/bigcode-datasets.ipynb
notebooks/bigcode-training.ipynb
notebooks/eda-paper.ipynb
notebooks/eval-loss.png
notebooks/filtered-umap.png
notebooks/full-umap.png
notebooks/preprocessed-dataset-final-results.json
notebooks/scc-smol-final-results.json
notebooks/train-loss.png
notebooks/umap-datasets.ipynb
notebooks/wandbplot.ipynb
tests/__init__.py
tests/test_downloader.py
tests/test_estimator.py
tests/test_version.py
tests/resources/test-manifest.yaml