Skip to content

Commit

Permalink
feat: add unsloth finetuning notebookt and llamacpp server
Browse files Browse the repository at this point in the history
- Add a notebook to finetune and quantize the LLM
- Add a llamacpp server serving the model in 4 bit
- Add Dockerfile and CI/CD building the image
- Add quality and testing in the CI
  • Loading branch information
bastienp committed Aug 19, 2024
1 parent 8f12a7d commit 0069489
Show file tree
Hide file tree
Showing 14 changed files with 16,259 additions and 0 deletions.
166 changes: 166 additions & 0 deletions .dockerignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,166 @@
_skbuild/

.envrc

models/

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
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/
cover/

# 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
.pybuilder/
target/

# Jupyter Notebook
.ipynb_checkpoints

# IPython
profile_default/
ipython_config.py

# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .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

# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# 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

# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml

# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__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/

# pytype static type analyzer
.pytype/

# Cython debug symbols
cython_debug/

# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
.idea/
94 changes: 94 additions & 0 deletions .github/workflows/cicd.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
name: CI/CD
run-name: ${{ github.actor }} is triggering CI/CD Action
on:
push:
branches:
- main
- 'releases/**'
pull_request:

env:
UV_SYSTEM_PYTHON: 1
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository }}
UV_CACHE_DIR: /tmp/.uv-cache

jobs:
code_quality:
name: Check code quality
runs-on: ubuntu-latest

steps:
- uses: actions/checkout@v4

- name: Set up uv
run: curl -LsSf https://astral.sh/uv/install.sh | sh

- name: Install dependencies
run: uv tool install ruff==0.6.1

- name: Check ruff formatting
run: uv run ruff format --config pyproject.toml --line-length 88 --exclude src/notebook .

- name: Check ruff linting
run: uv run ruff check --fix --respect-gitignore --config pyproject.toml --exclude src/notebook .

api_test:
name: Test API
runs-on: ubuntu-latest
needs: [ code_quality ]

steps:
- uses: actions/checkout@v4

- name: Set up uv
run: curl -LsSf https://astral.sh/uv/install.sh | sh

- name: Install dependencies
run: uv sync --extra test

- name: Run API tests
run: uv run pytest .

build-and-push-image:
name: Build and push Docker image
runs-on: ubuntu-latest
needs: [ api_test, code_quality ]
permissions:
contents: read
packages: write
attestations: write
id-token: write

steps:
- name: Checkout repository
uses: actions/checkout@v4

- name: Log in to the Container registry
uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@8e5442c4ef9f78752691e2d8f8d19755c6f78e81
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}

- name: Build and push Docker image
id: push
uses: docker/build-push-action@5cd11c3a4ced054e52742c5fd54dca954e0edd85
with:
context: .
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}

- name: Generate artifact attestation
uses: actions/[email protected]
with:
subject-name: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME}}
subject-digest: ${{ steps.push.outputs.digest }}
push-to-registry: true
Loading

0 comments on commit 0069489

Please sign in to comment.