Delta Vector Austral 70B Winton GGUF

🚀 Llamacpp imatrix Quantizations of Austral-70B-Winton by Delta-Vector

This project provides Llama.cpp imatrix quantizations of the Austral-70B-Winton model by Delta-Vector. It uses specific llama.cpp releases for quantization and offers various quantized models for different use - cases.

📋 Metadata

🚀 Quick Start

• Using llama.cpp release b5753 for quantization.
• Original model: https://huggingface.co/Delta-Vector/Austral-70B-Winton
• 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

💻 Usage Examples

Prompt format

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

📦 Installation

Download a file (not the whole branch) from below:

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/Delta-Vector_Austral-70B-Winton-GGUF --include "Delta-Vector_Austral-70B-Winton-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/Delta-Vector_Austral-70B-Winton-GGUF --include "Delta-Vector_Austral-70B-Winton-Q8_0/*" --local-dir ./

📚 Documentation

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 specific llama.cpp releases for quantization and provides various quantized models. The quantization method for some models uses Q8_0 for embed and output weights. There are also features like 'online repacking' for weights to improve performance on ARM and AVX machines.

📄 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