0cec062a63
* add glm edge chat model * use config partial_rotary_factor as rope ratio * support for glm edge model * vision model support * remove debug info * fix format * llava.cpp trailing whitespace * remove unused AutoTokenizer * Update src/llama.cpp for not contain <|end|> or </s> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> * add edge template * fix chat template * fix confict * fix confict * fix ci err * fix format err * fix template err * 9b hf chat support * format * format clip.cpp * fix format * Apply suggestions from code review * Apply suggestions from code review * Update examples/llava/clip.cpp * fix format * minor : style --------- Co-authored-by: liyuhang <yuhang.li@zhipuai.cn> Co-authored-by: piDack <pcdack@hotmail.co> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> Co-authored-by: liyuhang <yuhang.li@aminer.cn> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> |
||
|---|---|---|
| .. | ||
| examples | ||
| gguf | ||
| tests | ||
| LICENSE | ||
| pyproject.toml | ||
| README.md | ||
gguf
This is a Python package for writing binary files in the GGUF (GGML Universal File) format.
See convert_hf_to_gguf.py as an example for its usage.
Installation
pip install gguf
API Examples/Simple Tools
examples/writer.py — Generates example.gguf in the current directory to demonstrate generating a GGUF file. Note that this file cannot be used as a model.
examples/reader.py — Extracts and displays key-value pairs and tensor details from a GGUF file in a readable format.
gguf/scripts/gguf_dump.py — Dumps a GGUF file's metadata to the console.
gguf/scripts/gguf_set_metadata.py — Allows changing simple metadata values in a GGUF file by key.
gguf/scripts/gguf_convert_endian.py — Allows converting the endianness of GGUF files.
gguf/scripts/gguf_new_metadata.py — Copies a GGUF file with added/modified/removed metadata values.
Development
Maintainers who participate in development of this package are advised to install it in editable mode:
cd /path/to/llama.cpp/gguf-py
pip install --editable .
Note: This may require to upgrade your Pip installation, with a message saying that editable installation currently requires setup.py.
In this case, upgrade Pip to the latest:
pip install --upgrade pip
Automatic publishing with CI
There's a GitHub workflow to make a release automatically upon creation of tags in a specified format.
- Bump the version in
pyproject.toml. - Create a tag named
gguf-vx.x.xwherex.x.xis the semantic version number.
git tag -a gguf-v1.0.0 -m "Version 1.0 release"
- Push the tags.
git push origin --tags
Manual publishing
If you want to publish the package manually for any reason, you need to have twine and build installed:
pip install build twine
Then, follow these steps to release a new version:
- Bump the version in
pyproject.toml. - Build the package:
python -m build
- Upload the generated distribution archives:
python -m twine upload dist/*
Run Unit Tests
From root of this repository you can run this command to run all the unit tests
python -m unittest discover ./gguf-py -v
TODO
- Include conversion scripts as command line entry points in this package.