Merge pull request #37 from chanind/pypi-package

feat: pypi packaging and auto-release with semantic release

Author: saprmarks

.github/workflows/build.yml

@@ -0,0 +1,90 @@
+name: build
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Cache Huggingface assets
+        uses: actions/cache@v4
+        with:
+          key: huggingface-0-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/pyproject.toml') }}
+          path: ~/.cache/huggingface
+          restore-keys: |
+            huggingface-0-${{ runner.os }}-${{ matrix.python-version }}-
+      - name: Load cached Poetry installation
+        id: cached-poetry
+        uses: actions/cache@v4
+        with:
+          path: ~/.local # the path depends on the OS
+          key: poetry-${{ runner.os }}-${{ matrix.python-version }}-1 # increment to reset cache
+      - name: Install Poetry
+        if: steps.cached-poetry.outputs.cache-hit != 'true'
+        uses: snok/install-poetry@v1
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+      - name: Load cached venv
+        id: cached-poetry-dependencies
+        uses: actions/cache@v4
+        with:
+          path: .venv
+          key: venv-0-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/pyproject.toml') }}
+          restore-keys: |
+            venv-0-${{ runner.os }}-${{ matrix.python-version }}-
+      - name: Install dependencies
+        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+        run: poetry install --no-interaction
+      - name: Run Unit Tests
+        run: poetry run pytest tests/unit
+      - name: Build package
+        run: poetry build
+
+  release:
+    needs: build
+    permissions:
+      contents: write
+      id-token: write
+    # https://github.community/t/how-do-i-specify-job-dependency-running-in-another-workflow/16482
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main' && !contains(github.event.head_commit.message, 'chore(release):')
+    runs-on: ubuntu-latest
+    concurrency: release
+    environment:
+      name: pypi
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Semantic Release
+        id: release
+        uses: python-semantic-release/[email protected]
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        if: steps.release.outputs.released == 'true'
+      - name: Publish package distributions to GitHub Releases
+        uses: python-semantic-release/upload-to-gh-release@main
+        if: steps.release.outputs.released == 'true'
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -99,7 +99,7 @@ ipython_config.py
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
+poetry.lock
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.

README.md

@@ -8,13 +8,9 @@ Some dictionaries trained using this repository (and associated training checkpo
 
 Navigate to the to the location where you would like to clone this repo, clone and enter the repo, and install the requirements.
 ```bash
-git clone https://github.com/saprmarks/dictionary_learning
-cd dictionary_learning
-pip install -r requirements.txt
+pip install dictionary-learning
 ```
 
-To use `dictionary_learning`, include it as a subdirectory in some project's directory and import it; see the examples below.
-
 We also provide a [demonstration](https://github.com/adamkarvonen/dictionary_learning_demo), which trains and evaluates 2 SAEs in ~30 minutes before plotting the results.
 
 # Using trained dictionaries

__init__.py

@@ -0,0 +1,6 @@
+__version__ = "0.1.0"
+
+from .dictionary import AutoEncoder, GatedAutoEncoder, JumpReluAutoEncoder
+from .buffer import ActivationBuffer
+
+__all__ = ["AutoEncoder", "GatedAutoEncoder", "JumpReluAutoEncoder", "ActivationBuffer"]