🎉 first commit

.flake8

@@ -0,0 +1,9 @@
+[flake8]
+max-line-length = 100
+extend-ignore = E203
+per-file-ignores = **/__init__.py:F401
+exclude =
+    .git,
+    __pycache__,
+    build,
+    dist,

.gitignore

@@ -0,0 +1,150 @@
+### Custom .gitignore ###
+# Data stuff
+*/*/data
+
+# IDE stuff
+.idea/
+.vscode/
+
+### GitHub's .gitignore Python template ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+datasets/*/data
+datasets/**/resources
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+#logs
+
+/**/**/outputs
+/**/**/wandb
+/**/logs/**
+/**/multirun
+
+#custom extension
+*.bak
+**/e3c_llm/data/*

.pre-commit-config.yaml

@@ -0,0 +1,68 @@
+# This file defines all the hooks run by pre-commit.
+
+exclude: "poetry.lock"
+
+repos:
+  # Base pre-commit hook repository, for simple checks & fixes
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: check-added-large-files # Prevent giant files from being committed
+      - id: check-ast # Check whether the files parse as valid Python
+      - id: check-json # Check JSON files for parseable syntax
+      - id: check-merge-conflict # Check for files that contain merge conflict strings
+      - id: check-toml # Checks TOML files for parseable syntax
+      - id: check-yaml # Check YAML files for parseable syntax
+      - id: debug-statements # Check for debugger imports and `breakpoint()` calls in python
+      - id: detect-private-key # Detect the presence of private keys
+      - id: end-of-file-fixer # Ensures that files end with a newline
+      - id: name-tests-test # Verify that test files are named correctly
+        exclude: tests/utils/
+
+  # Black is used to format the code in Python
+  - repo: https://github.com/psf/black
+    rev: 22.12.0
+    hooks:
+      - id: black
+
+  # Isort is used to re-organize our import statements in Python
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        args: ["--resolve-all-configs"]
+
+  # nbstripout is used to remove Jupyter notebooks' cell outputs
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.6.1
+    hooks:
+      - id: nbstripout
+
+  # Prettier is a formatting tool for many non-Python files
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v3.0.0-alpha.4
+    hooks:
+      - id: prettier
+
+  # TOML-sort is used to re-organize alphabetically TOML files (such as pyproject.toml)
+  - repo: https://github.com/pappasam/toml-sort
+    rev: v0.22.1
+    hooks:
+      - id: toml-sort
+        args: ["--all", "--in-place"]
+
+  # Flake8 is used to perform various code sanity checks in Python
+  - repo: https://github.com/pycqa/flake8
+    rev: 6.0.0
+    hooks:
+      - id: flake8
+        exclude: notebooks/
+
+  # Mypy is used to check the typing hints in Python; it is quite a restrictive tool, so we don't
+  # use it in tests
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.991
+    hooks:
+      - id: mypy
+        exclude: apps/|notebooks/|tests/
+        additional_dependencies: ["types-requests"]

.project-root

@@ -0,0 +1,2 @@
+# this file is required for inferring the project root directory
+# do not delete

Dockerfile

@@ -0,0 +1,48 @@
+# Build: sudo docker build -t <project_name> .
+# Run: sudo docker run -v $(pwd):/workspace/project --gpus all -it --rm <project_name>
+
+
+FROM nvidia/cuda:12.0.0-devel-ubuntu20.04
+
+
+ENV CONDA_ENV_NAME=myenv
+ENV PYTHON_VERSION=3.9
+
+
+# Basic setup
+RUN apt update
+RUN apt install -y zsh \
+    build-essential \
+    git \
+    curl \
+    ca-certificates \
+    wget \
+    && rm -rf /var/lib/apt/lists
+RUN wget https://github.com/robbyrussell/oh-my-zsh/raw/master/tools/install.sh -O - | zsh || true
+
+# Set working directory
+WORKDIR /workspace/project
+
+
+# Install Miniconda and create main env
+ADD https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh miniconda3.sh
+RUN bash miniconda3.sh -b -p /conda \
+    && echo export PATH=/conda/bin:$PATH >> .zshrc \
+    && rm miniconda3.sh
+ENV PATH="/conda/bin:${PATH}"
+RUN conda create -n ${CONDA_ENV_NAME} python=${PYTHON_VERSION}
+
+
+# Switch to zsh shell
+SHELL ["/bin/zsh", "-c"]
+
+
+# Install requirements
+COPY pyproject.toml ./
+RUN source activate ${CONDA_ENV_NAME} \
+    && pip install poetry \
+    && poetry install
+
+
+# Set ${CONDA_ENV_NAME} to default virutal environment
+RUN echo "source activate ${CONDA_ENV_NAME}" >> ~/.zshrc