File tree Expand file tree Collapse file tree 1 file changed +13
-8
lines changed Expand file tree Collapse file tree 1 file changed +13
-8
lines changed Original file line number Diff line number Diff line change 1
- AutoGGUF - Automated GGUF Model Quantizer
1
+ # AutoGGUF - automated GGUF model quantizer
2
2
3
3
This application provides a graphical user interface for quantizing GGUF models
4
4
using the llama.cpp library. It allows users to download different versions of
5
5
llama.cpp, manage multiple backends, and perform quantization tasks with various
6
6
options.
7
7
8
- Main features:
8
+ ** Main features** :
9
9
1 . Download and manage llama.cpp backends
10
10
2 . Select and quantize GGUF models
11
11
3 . Configure quantization parameters
12
12
4 . Monitor system resources during quantization
13
13
14
- Usage:
15
- Run the main.py script to start the application.
14
+ ** Usage** :
15
+ 1 . Install dependencies, either using the ` requirements.txt ` file or ` pip install PyQt6 requests psutil ` .
16
+ 2 . Run the ` run.bat ` script to start the application, or run the command ` python src/main.py ` .
16
17
17
- Dependencies:
18
+ ** Dependencies** :
18
19
- PyQt6
19
20
- requests
20
21
- psutil
21
22
22
- Author: leafspark
23
- Version: 1.0.0
24
- License: apache-2.0
23
+ ** To be implemented:**
24
+ - Actual progress bar tracking
25
+ - Download safetensors from HF and convert to unquanted GGUF
26
+ - Specify multiple KV overrides
27
+
28
+ ** User interface:**
29
+ ![ image] ( https://github.com/user-attachments/assets/b1b58cba-4314-479d-a1d8-21ca0b5a8935 )
You can’t perform that action at this time.
0 commit comments