FantasiaFoundry
commited on
Commit
•
31666cd
1
Parent(s):
3278c0b
Fix lines.
Browse files
README.md
CHANGED
@@ -21,11 +21,11 @@ Pull Requests with your own features and improvements to this script are always
|
|
21 |
|
22 |
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.
|
23 |
|
24 |
-
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
|
25 |
|
26 |
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.
|
27 |
|
28 |
-
Adjust `quantization_options` in [**line
|
29 |
|
30 |
> [!NOTE]
|
31 |
> 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.
|
|
|
21 |
|
22 |
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.
|
23 |
|
24 |
+
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 135**](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script/blob/main/gguf-imat.py#L120). 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.
|
25 |
|
26 |
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.
|
27 |
|
28 |
+
Adjust `quantization_options` in [**line 163**](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script/blob/main/gguf-imat.py#L133).
|
29 |
|
30 |
> [!NOTE]
|
31 |
> 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.
|