GGUF caller
Project description
GGUF model caller
This package is a GGUF (GPT-Generated Unified Format) file/model caller.
install the caller via pip/pip3 (once only):
pip install callgg
update the caller (if not in the latest version) by:
pip install callgg --upgrade
user manual
This is a cmd-based (command line) package, you can find the user manual by adding the flag -h or --help.
callgg -h
call gguf-selector for running a GGUF model/file:
callgg run
GGUF file(s) in the same directory will automatically be detected by the caller, hence, a selection menu will be shown in the console as below.
sample model(s) available to download (try out)
For general purpose [chat.gguf] (file size: around 2GB or less)
callgg save https://huggingface.co/calcuis/chat/resolve/main/chat.gguf
For coding [code.gguf] (file size: around 3GB or more)
callgg save https://huggingface.co/calcuis/chat/resolve/main/code.gguf
For health/medical advice [medi.gguf] (file size: around 3GB or more)
callgg save https://huggingface.co/calcuis/chat/resolve/main/medi.gguf
***those are all experimental models; no guarantee on quality
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
callgg-1.0.0.tar.gz
(3.3 kB
view hashes)
Built Distribution
Close
Hashes for callgg-1.0.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 475d8f9d02601cd40245fa43013ee31fc3d95248ef922df8dc36d83d0f4f5092 |
|
MD5 | 02efbbf4679c6d755c6ed4d72b67c538 |
|
BLAKE2b-256 | c814c732dbe232fe1a3ebcbd6a5a1b3d97435776537349c09a49fe47472ca5b8 |