Andrewzh Absolute Zero Reasoner Coder 7b GGUF

🚀 Llamacpp imatrix Quantizations of Absolute_Zero_Reasoner-Coder-7b by andrewzh

This project provides Llama.cpp imatrix quantizations of the Absolute_Zero_Reasoner-Coder-7b model. It enables more efficient use of the model on various hardware platforms, offering multiple quantization types to balance between quality and resource consumption.

✨ Features

• Multiple Quantization Types: Offers a wide range of quantization types, such as bf16, Q8_0, Q6_K_L, etc., to meet different quality and resource requirements.
• Easy to Use: Can be run in LM Studio or directly with Llama.cpp and other Llama.cpp-based projects.
• Online Repacking: Supports online repacking of weights for better performance on ARM and AVX machines.

🚀 Quick Start

Running the Model

• LM Studio: You can run the quantized models in LM Studio.
• Llama.cpp: Run them directly with Llama.cpp, or any other Llama.cpp-based project.

Prompt Format

{system_prompt}
{prompt}

📦 Installation

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/andrewzh_Absolute_Zero_Reasoner-Coder-7b-GGUF --include "andrewzh_Absolute_Zero_Reasoner-Coder-7b-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/andrewzh_Absolute_Zero_Reasoner-Coder-7b-GGUF --include "andrewzh_Absolute_Zero_Reasoner-Coder-7b-Q8_0/*" --local-dir ./

💻 Usage Examples

Download a file (not the whole branch)

🔧 Technical Details

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.