Thedrummer Anubis 70B V1.1 GGUF

🚀 Llamacpp imatrix Quantizations of Anubis-70B-v1.1 by TheDrummer

This project provides quantized versions of the Anubis-70B-v1.1 model using llama.cpp, offering various quantization types for different performance and quality requirements.

🚀 Quick Start

• Using llama.cpp: The quantizations are created with llama.cpp release b5753.
• Running in LM Studio: You can run the quantized models in LM Studio.
• Running directly with llama.cpp: Or use them directly with llama.cpp or any other llama.cpp - based project.

✨ Features

• Multiple Quantization Types: Offers a wide range of quantization types, such as Q8_0, Q6_K, Q5_K_M, etc., to balance between quality and file size.
• Online Repacking: Some quantization types support online repacking for better performance on ARM and AVX machines.

📦 Installation

Download a file (not the whole branch)

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/TheDrummer_Anubis-70B-v1.1-GGUF --include "TheDrummer_Anubis-70B-v1.1-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/TheDrummer_Anubis-70B-v1.1-GGUF --include "TheDrummer_Anubis-70B-v1.1-Q8_0/*" --local-dir ./

💻 Usage Examples

Prompt format

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

Cutting Knowledge Date: December 2023
Today Date: 26 Jul 2024

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

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

📚 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 quantizations are based on the llama.cpp library, using the imatrix option with a specific calibration dataset. The online repacking feature for weights in Q4_0 is an important technical aspect, which can improve performance on ARM and AVX machines.

📄 License

No license information is provided in the original README.

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