mirror of https://github.com/leafspark/AutoGGUF
50 lines
1.5 KiB
Markdown
50 lines
1.5 KiB
Markdown
# AutoGGUF - automated GGUF model quantizer
|
|
|
|
This application provides a graphical user interface for quantizing GGUF models
|
|
using the llama.cpp library. It allows users to download different versions of
|
|
llama.cpp, manage multiple backends, and perform quantization tasks with various
|
|
options.
|
|
|
|
**Main features**:
|
|
1. Download and manage llama.cpp backends
|
|
2. Select and quantize GGUF models
|
|
3. Configure quantization parameters
|
|
4. Monitor system resources during quantization
|
|
|
|
**Usage**:
|
|
|
|
Cross platform:
|
|
1. Install dependencies, either using the `requirements.txt` file or `pip install PyQt6 requests psutil`.
|
|
2. Run the `run.bat` script to start the application, or run the command `python src/main.py`.
|
|
|
|
Windows:
|
|
1. Download latest release, extract all to folder and run `AutoGGUF.exe`
|
|
2. Enjoy!
|
|
|
|
**Building**:
|
|
```
|
|
cd src
|
|
pip install -U pyinstaller
|
|
pyinstaller main.py
|
|
cd dist/main
|
|
main
|
|
```
|
|
|
|
**Dependencies**:
|
|
- PyQt6
|
|
- requests
|
|
- psutil
|
|
|
|
**Issues:**
|
|
- Actual progress bar tracking
|
|
- Download safetensors from HF and convert to unquanted GGUF
|
|
- ~~Specify multiple KV overrides~~ (added in v1.1.0)
|
|
- ~~Better error handling~~ (added in v1.1.0)
|
|
- ~~Cannot select output/token embd type~~ (fixed in v1.1.0)
|
|
|
|
**Troubleshooting:**
|
|
- llama.cpp quantizations errors out with an iostream error: create the `quantized_models` directory (or set a directory)
|
|
|
|
**User interface:**
|
|
|