add docker compose for running locally

.dockerignore

@@ -0,0 +1,2 @@
+/downloads
+/llama.cpp

.gitignore

@@ -0,0 +1,166 @@
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+/downloads
+!/downloads/.keep
+/llama.cpp

Dockerfile

@@ -60,5 +60,5 @@ ENV PYTHONPATH=${HOME}/app \
     PATH=/usr/local/nvidia/bin:${PATH}
 
 
-ENTRYPOINT /bin/sh start.sh
+ENTRYPOINT /bin/bash start.sh
 

README.md

@@ -13,3 +13,7 @@ pinned: false
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+To run this space locally:
+1. Login huggingface CLI: `huggingface-cli login`
+2. Run command: `HF_TOKEN=$(cat ~/.cache/huggingface/token) docker compose up`

docker-compose.yml

@@ -0,0 +1,16 @@
+# Docker compose file to LOCAL development
+
+services:
+  gguf-my-repo:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    image: gguf-my-repo
+    container_name: gguf-my-repo
+    ports:
+      - "7860:7860"
+    volumes:
+      - .:/home/user/app
+    environment:
+      - RUN_LOCALLY=1
+      - HF_TOKEN=${HF_TOKEN}

start.sh

@@ -1,5 +1,17 @@
+#!/bin/bash
+
+if [ ! -d "llama.cpp" ]; then
+  # only run in dev env
+  git clone https://github.com/ggerganov/llama.cpp
+fi
+
+if [[ -z "${RUN_LOCALLY}" ]]; then
+  # enable CUDA if NOT running locally
+  export LLAMA_CUDA=1
+fi
+
 cd llama.cpp
-LLAMA_CUDA=1 make -j llama-quantize llama-gguf-split llama-imatrix
+make -j llama-quantize llama-gguf-split llama-imatrix
 
 cd ..
-python app.py
+python app.py