Delta Vector Austral 24B Winton GGUF

🚀 Llamacpp imatrix Quantizations of Austral-24B-Winton by Delta-Vector

This project provides quantized versions of the Austral-24B-Winton model. It uses llama.cpp for quantization, enabling efficient deployment on various hardware. The quantized models can be run in LM Studio or directly with llama.cpp.

✨ Features

• Quantization: Utilizes llama.cpp release b5669 for quantization.
• Multiple Quant Types: Offers a wide range of quant types to balance between quality and file size.
• Online Repacking: Supports online repacking of weights for improved performance on ARM and AVX machines.

📦 Installation

Prerequisites

Make sure you have huggingface-cli installed:

pip install -U "huggingface_hub[cli]"

Downloading a Single File

To download a specific file, run the following command:

huggingface-cli download bartowski/Delta-Vector_Austral-24B-Winton-GGUF --include "Delta-Vector_Austral-24B-Winton-Q4_K_M.gguf" --local-dir ./

Downloading Split Files

If the model is split into multiple files (models bigger than 50GB), use the following command to download all files to a local folder:

huggingface-cli download bartowski/Delta-Vector_Austral-24B-Winton-GGUF --include "Delta-Vector_Austral-24B-Winton-Q8_0/*" --local-dir ./

💻 Usage Examples

Running in LM Studio

You can run the quantized models in LM Studio.

Running with llama.cpp

Run the models directly with llama.cpp, or any other llama.cpp based project.

Prompt Format

No chat template is specified, so the default is used. This may be incorrect, check the original model card for details.

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

📚 Documentation

Download a File

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Which file should I choose?

🔧 Technical Details

• Quantization Method: Using llama.cpp release b5669 for quantization.
• Dataset: All quants are made using the imatrix option with the dataset from here.

📄 License

This project is licensed under the Apache-2.0 license.

Credits

• Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
• Thank you ZeroWw for the inspiration to experiment with embed/output.
• Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski