Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-06 02:48:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

gguf : update readme with build notes

Browse Source
This commit is contained in:
M. Yusuf Sarıgöz 2023-08-25 09:02:36 +03:00
parent 3e98cbe76e
commit 8798aea247
1 changed files with 23 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
gguf-py/README.md
View File

@ -6,7 +6,7 @@ This is a Python package for writing binary files in the [GGUF](https://github.c
See [convert-llama-hf-to-gguf.py](https://github.com/ggerganov/llama.cpp/blob/master/convert-llama-hf-to-gguf.py) See [convert-llama-hf-to-gguf.py](https://github.com/ggerganov/llama.cpp/blob/master/convert-llama-hf-to-gguf.py)
as an example for its usage. as an example for its usage.
## Install ## Installation
```sh ```sh
pip install gguf pip install gguf
``` ```
@ -14,7 +14,6 @@ pip install gguf
## Development ## Development
Maintainers who participate in development of this package are advised to install it in editable mode: Maintainers who participate in development of this package are advised to install it in editable mode:
```sh ```sh
cd /path/to/llama.cpp/gguf-py cd /path/to/llama.cpp/gguf-py
@ -28,7 +27,28 @@ In this case, upgrade Pip to the latest:
pip install --upgrade pip pip install --upgrade pip
``` ```
## TODO ## Publishing
To publish the package, you need to have `twine` and `build` installed:
```sh
pip install build twine
```
Then, folow these steps to release a new version:
1. Update versions in `pyproject.toml` and `__init__.py`.
2. Build the package:
```sh
python -m build
```
3. Upload the generated distribution archives:
```sh
python -m twine upload dist/*
```
## TODO
- [ ] Add tests - [ ] Add tests
- [ ] Include conversion scripts as command line entry points in this package. - [ ] Include conversion scripts as command line entry points in this package.