| | --- |
| | license: cc-by-nc-4.0 |
| | --- |
| | Simple python script (`gguf-imat.py`) to generate various GGUF-Imatrix quantizations from a Hugging Face `author/model` input, for Windows and NVIDIA hardware. |
| |
|
| | This is setup for a Windows machine with 8GB of VRAM, assuming use with an NVIDIA GPU. If you want to change the the `-ngl` (number of GPU layers) amount, you can do so at **line 120**. This is only relevant during the `--imatrix` data generation. If you don't have enough VRAM you can decrease the `-ngl` amount or set it to 0 to only use your System RAM instead for all layers. |
| |
|
| | Your `imatrix.txt` is expected to be located inside the `imatrix` folder. Included file is considered a good option, [this discussion](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) is where it came from. |
| |
|
| | Adjust `quantization_options` in **line 133**. |
| |
|
| | **Requirements:** |
| | - Python 3.11 |
| | - `pip install huggingface_hub` |
| | <br><br> |
| |
|
| | **If this proves useful for you, feel free to credit and share the repository.** |
