mirror of
https://github.com/ivabus/pantry
synced 2024-11-27 02:35:08 +03:00
21 lines
463 B
Markdown
21 lines
463 B
Markdown
|
# getting started
|
||
|
|
|
||
|
|
```sh
|
||
|
|
$ llama.cpp
|
||
|
|
# ^^ default chat prompt with the OpenLLaMA model
|
||
|
|
```
|
||
|
|
|
||
|
|
If you want to run `llama.cpp` with your own args specify them and chat mode
|
||
|
|
will be skipped.
|
||
|
|
|
||
|
|
If you want to use a different model specify `--model`.
|
||
|
|
|
||
|
|
# 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
|
||
|
|
tea +github.com/ggerganov/llama.cpp convert.py path/to/your/model
|
||
|
|
```
|