ctransformer-core

Follow up the stopping updated project ctransformers; continue working on it.

install it by (pip/pip3):

pip install ctransformers-0.2.28.tar.gz

run it by (python/python3):

python -m ctransformers

User interfaces are available to choose (eithr CLI or GUI); while chosen, GGUF file(s) in the current directory will be searched and detected.

This is another solo connector core; same as llama-core; being able to work independently as well.

reference

ctransformers

All other functions are same as ctransformers; please see the reference above.

build from ctransformers-0.2.28.tar.gz (examples below are for CPU)

According to the latest note inside vs code, msys64 is recommended by Microsoft; or you can opt w64devkit or etc. as source of your gcc and g++ compilers.

for windows user(s):

$env:CMAKE_GENERATOR = "MinGW Makefiles"
$env:CMAKE_ARGS = "-DCMAKE_C_COMPILER=C:/msys64/mingw64/bin/gcc.exe -DCMAKE_CXX_COMPILER=C:/msys64/mingw64/bin/g++.exe"
pip install ctransformers-0.2.28.tar.gz

In mac, xcode command line tools are recommended by Apple for dealing all coding related issue(s); or you can bypass it for your own good/preference.

for mac user(s):

pip3 install ctransformers-0.2.28.tar.gz

Make sure your gcc and g++ are >=11; you can check it by: gcc --version and g++ --version if you opt to build the wheel from source code.