| | --- |
| | license: cc-by-nc-4.0 |
| | inference: false |
| | pipeline_tag: text-generation |
| | tags: |
| | - gguf |
| | - quantized |
| | - text-generation-inference |
| | --- |
| | |
| | > [!TIP] |
| | > **Credits:** <br> |
| | > Made with love by [**@Lewdiculous**](https://huggingface.co/Lewdiculous). <br> |
| | > *If this proves useful for you, feel free to credit and share the repository and authors.* |
| |
|
| | > [!WARNING] |
| | > **Warning:** <br> |
| | > For **Llama-3** models that don't follow the ChatML, Alpaca, Vicuna and other conventional formats, at the moment, you have to use `gguf-imat-llama-3.py` and replace the config files with the ones in the [**ChaoticNeutrals/Llama3-Corrections**](https://huggingface.co/ChaoticNeutrals/Llama3-Corrections/tree/main) repository to properly quant and generate the imatrix data. |
| |
|
| | Pull Requests with your own features and improvements to this script are always welcome. |
| |
|
| | # GGUF-IQ-Imatrix-Quantization-Script: |
| |
|
| |  |
| |
|
| | 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 `-ngl` (number of GPU layers) amount, you can do so at [**line 124**](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script/blob/main/gguf-imat.py#L124). 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, this will make the imatrix data generation take longer, so it's a good idea to find the number that gives your own machine the best results. |
| |
|
| | Your `imatrix.txt` is expected to be located inside the `imatrix` folder. I have already included a file that is considered a good starting option, [this discussion](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) is where it came from. If you have suggestions or other imatrix data to recommend, please do so. |
| |
|
| | Adjust `quantization_options` in [**line 138**](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script/blob/main/gguf-imat.py#L138). |
| |
|
| | > [!NOTE] |
| | > Models downloaded to be used for quantization are cached at `C:\Users\{{User}}\.cache\huggingface\hub`. You can delete these files manually as needed after you're done with your quantizations, you can do it directly from your Terminal if you prefer with the `rmdir "C:\Users\{{User}}\.cache\huggingface\hub"` command. You can put it into another script or alias it to a convenient command if you prefer. |
| |
|
| |
|
| | **Hardware:** |
| |
|
| | - NVIDIA GPU with 8GB of VRAM. |
| | - 32GB of system RAM. |
| |
|
| | **Software Requirements:** |
| | - Git |
| | - 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> |
