| license: cc-by-nc-4.0 | |
| inference: false | |
| pipeline_tag: text-generation | |
| tags: | |
| - gguf | |
| - quantized | |
| - text-generation-inference | |
| Simple python script (`gguf-imat.py`) to generate various GGUF-IQ-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` | |
| **Usage:** | |
| ``` | |
| python .\gguf-imat.py | |
| ``` | |
| Quantizations will be output into the created `models\{model-name}-GGUF` folder. | |
| <br><br> | |
| **If this proves useful for you, feel free to credit and share the repository.** |