pantry/projects/github.com/ggerganov/llama.cpp/README.md
James Reynolds 2b06942c62
GitHub.com/ggerganov/llama.cpp update (#3696)
* llama.cpp, github version instead of hardcoded version
* llama.cpp, check if model is specified, if yes, run it, if not, then download model
* Use entrypoint for custom llama.cpp invocation
* `llama.cpp` is just raw executable. This I think is our new pattern.
* To run chat use the entrypoint: `pkgx +brewkit -- run llama.cpp`

Co-authored-by: James Reynolds <magnsuviri@me.com>
Co-authored-by: Max Howell <mxcl@me.com>
2023-10-26 07:24:04 -04:00

21 lines
512 B
Markdown

# getting started
```sh
$ pkgx +brewkit -- run llama.cpp
# ^^ default chat prompt with an appropriate hugging face model
```
If you want to run `llama.cpp` with your own args `pkgx llama.cpp $ARGS` is
your friend.
# converting your own models
We provide a working `convert.py` from the llama.cpp project. To use it you
need to launch it via a tea pkgenv:
```sh
pkgx +llama.cpp -- convert.py path/to/your/model
# ^^ the -- is necessary since `convert.py` is a not listed in the llama.cpp
# provides list
```