why i cant load the model?
#Llama.cpp
silent socket
ruby solar
Your CPU does not support AVX2 instructions. Run cmd_windows.bat and enter these commands:
set FORCE_CMAKE=1
set "CMAKE_ARGS=-DLLAMA_AVX2=off"
python -m pip install git+https://github.com/abetlen/[email protected] --force-reinstall --no-deps
python -m pip install llama-cpp-python-cuda --force-reinstall --no-deps --index-url=https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/textgen/AVX/cu117
The first 3 commands require that you install Visual Studio Build Tools with Desktop C++ option selected in the installer. They may not be necessary if you have an NVIDIA GPU.
silent socket
Your CPU does not support AVX2 instructions. Run `cmd_windows.bat` and enter the...
thanks, i will try it, but if i had a problem or didnt know how to do it, can i DM you?
ruby solar
Sure. I am planning on building CPU-only versions of llama-cpp-python compiled without AVX2 for people to use. So, it should be easier to fix this issue in the future.
silent socket
well i love to.
is this the right one? and on the right side, which option should i check? (i have a slow internet so i probable need 6-12 hours just to download this GB)
ruby solar
is this the right one? and on the right side, which option should i check? (i ha...
Desktop development with C++