Andrewzh Absolute Zero Reasoner Coder 14b GGUF

🚀 Llamacpp imatrix Quantizations of Absolute_Zero_Reasoner-Coder-14b by andrewzh

This project provides Llama.cpp imatrix quantizations of the Absolute_Zero_Reasoner-Coder-14b model. It enables efficient deployment and utilization of the model in various environments.

🚀 Quick Start

Prerequisites

• Ensure you have a suitable environment to run the quantized models, such as LM Studio or a llama.cpp based project.

Usage

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

✨ Features

Quantization

• Using llama.cpp release b5338 for quantization.
• All quants made using imatrix option with dataset from here.

Original Model

• Original model: https://huggingface.co/andrewzh/Absolute_Zero_Reasoner-Coder-14b

📦 Installation

Download a file (not the whole branch)

You can download the specific quantized model files from the following table:

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/andrewzh_Absolute_Zero_Reasoner-Coder-14b-GGUF --include "andrewzh_Absolute_Zero_Reasoner-Coder-14b-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/andrewzh_Absolute_Zero_Reasoner-Coder-14b-GGUF --include "andrewzh_Absolute_Zero_Reasoner-Coder-14b-Q8_0/*" --local-dir ./

💻 Usage Examples

Prompt format

{system_prompt}
{prompt}

📚 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.