| For NVIDIA cards install the CUDA toolkit | |
| Nvidia Maxwell or higher | |
| https://developer.nvidia.com/cuda-downloads | |
| Nvidia Kepler or higher | |
| https://developer.nvidia.com/cuda-11-8-0-download-archive | |
| Restart your computer after installing the CUDA toolkit to make sure the PATH is set correctly. | |
| Haven't done much testing but for Windows, Visual Studio 2019 with desktop development for C++ might be required. | |
| https://visualstudio.microsoft.com/thank-you-downloading-visual-studio/?sku=community&rel=16&utm_medium=microsoft&utm_campaign=download+from+relnotes&utm_content=vs2019ga+button | |
| install the desktop development for C++ workload | |
| For Linux, install the build tools from your package manager. | |
| For example, on Ubuntu use: sudo apt-get install build-essential | |
| This may work with AMD cards but only on linux and possibly WSL2. I can't guarantee that it will work on AMD cards, I personally don't have one to test with. You may need to install stuff before starting. https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html | |
| First setup your environment by using either windows.bat or linux.sh. If something fails during setup, then every file and folder except for windows.bat, linux.sh, and exl2-quant.py should be deleted then try again. | |
| After setup is complete then you'll have a file called start-quant. Use this to run the quant script. | |
| Make sure that your storage space is 3x the amount of the model's size. To mesure this, take the number of billion parameters and mutliply by two, afterwards mutliply by 3 and that's the recommended storage. There's a chance you may get away with 2.5x the size as well. | |
| Make sure to also have a lot of RAM depending on the model. | |
| If you close the terminal or the terminal crashes, check the last BPW it was on and enter the remaining quants you wanted. It should be able to pick up where it left off. Don't type the BPW of completed quants as it will start from the beginning. You may also use ctrl + c pause at any time during the quant process. | |
| To add more options to the quantization process, you can add them to line 170. All options: https://github.com/turboderp/exllamav2/blob/master/doc/convert.md | |
| Things may break in the future as it downloads the latest version of all the dependencies which may either change names or how they work. If something breaks, please open a discussion at https://huggingface.co/Anthonyg5005/hf-scripts/discussions | |
| Credit to turboderp for creating exllamav2 and the exl2 quantization method. | |
| https://github.com/turboderp | |
| Credit to oobabooga the original download and safetensors scripts. | |
| https://github.com/oobabooga | |
| Credit to Lucain Pouget for maintaining huggingface-hub. | |
| https://github.com/Wauplin | |
| Only tested with CUDA 12.1 on Windows 11 and half-tested Linux through WSL2 but I don't have enough RAM to fully test but quantization did start. |