Beaverai MN 2407 DSK QwQify V0.1 12B GGUF

🚀 Llamacpp imatrix Quantizations of MN-2407-DSK-QwQify-v0.1-12B by BeaverAI

This project provides Llama.cpp imatrix quantizations of the MN-2407-DSK-QwQify-v0.1-12B model by BeaverAI, enabling efficient deployment and inference.

🚀 Quick Start

• Using llama.cpp release b4896 for quantization.
• Original model: https://huggingface.co/BeaverAI/MN-2407-DSK-QwQify-v0.1-12B
• All quants are made using the imatrix option with the dataset from here.
• Run them in LM Studio.
• Run them directly with llama.cpp, or any other llama.cpp based project.

✨ Features

Update Chat Template

The chat template has been updated to provide a better user experience.

📦 Installation

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-GGUF --include "BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-GGUF --include "BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-Q8_0/*" --local-dir ./

💻 Usage Examples

Prompt format

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

📚 Documentation

Model Information

Download a file (not the whole branch)

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

The project uses llama.cpp release b4896 for quantization. The quantization process involves using the imatrix option with a specific dataset. The embeddings and output weights of some quants are quantized to Q8_0 to improve performance.

📄 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