Initial commit after moving over from llama.cpp repo

Author: thomasantony

.gitignore

@@ -0,0 +1,164 @@
+# setup.py is auto-generated by poetry
+setup.py 
+
+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/

CMakeLists.txt

@@ -0,0 +1,27 @@
+# CmakeLists for building python bindings
+cmake_minimum_required(VERSION 3.0)
+
+project(llamacpp)
+
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_CXX_EXTENSIONS OFF)
+
+set(GGML_USE_ACCELERATE 1)
+find_package(pybind11 REQUIRED)
+
+add_library(llamacpp MODULE src/PyLlama.cpp ../llama.cpp ../ggml.c ../utils.cpp)
+
+target_include_directories(llamacpp PRIVATE ../)
+
+target_link_libraries(llamacpp PRIVATE pybind11::module pybind11::lto pybind11::windows_extras)
+add_link_options(-no_fixup_chains)
+pybind11_extension(llamacpp)
+
+if(NOT MSVC AND NOT ${CMAKE_BUILD_TYPE} MATCHES Debug|RelWithDebInfo)
+    # Strip unnecessary sections of the binary on Linux/macOS
+    pybind11_strip(llamacpp)
+endif()
+
+set_target_properties(llamacpp PROPERTIES CXX_VISIBILITY_PRESET "hidden"
+    CUDA_VISIBILITY_PRESET "hidden")

README.md

@@ -0,0 +1,60 @@
+## Building the Python bindings
+
+### macOS
+
+`brew install pybind11`
+
+## Install python package
+
+### From PyPI
+
+```
+pip install llamacpp
+```
+
+### From source
+
+```
+poetry install
+```
+
+## Get the model weights
+
+You will need to obtain the weights for LLaMA yourself. There are a few torrents floating around as well as some huggingface repositories (e.g https://huggingface.co/nyanko7/LLaMA-7B/). Once you have them, copy them into the models folder.
+
+```
+ls ./models
+65B 30B 13B 7B tokenizer_checklist.chk tokenizer.model
+```
+
+Convert the weights to GGML format using `llamacpp-convert`. Then use `llamacpp-quantize` to quantize them into INT4. For example, for the 7B parameter model, run
+
+```
+llamacpp-convert ./models/7B/ 1
+llamacpp-quantize ./models/7B/
+```
+
+## Run this demo script
+
+```
+import llamacpp
+import os
+
+model_path = "./models/7B/ggml-model-q4_0.bin"
+params = llamacpp.gpt_params(model_path,
+"Hi, I'm a llama.",
+4096,
+40,
+0.1,
+0.7,
+2.0)
+model = llamacpp.PyLLAMA(model_path, params)
+model.predict("Hello, I'm a llama.", 10)
+```
+
+## ToDo
+
+- [x] Use poetry to build package
+- [x] Add command line entry point for quantize script
+- [x] Publish wheel to PyPI
+- [ ] Add chat interface based on tinygrad

build.py

@@ -0,0 +1,16 @@
+from setuptools_cpp import CMakeExtension, ExtensionBuilder, Pybind11Extension
+from typing import Any, Dict
+
+
+def build(setup_kwargs: Dict[str, Any]) -> None:
+    ext_modules = [
+        CMakeExtension(f"llamacpp.llamacpp", sourcedir="./python"),
+    ]
+
+    setup_kwargs.update(
+        {
+            "ext_modules": ext_modules,
+            "cmdclass": dict(build_ext=ExtensionBuilder),
+            "zip_safe": False,
+        }
+    )

llamacpp/__init__.py

@@ -0,0 +1,2 @@
+# Expose the bindings in module
+from .llamacpp import gpt_params, PyLLAMA, llama_model_quantize