Llama 3 70B Instruct Abliterated GGUF

🚀 Llamacpp imatrix Quantizations of llama-3-70B-Instruct-abliterated

This project provides quantized versions of the llama-3-70B-Instruct-abliterated model using llama.cpp. It offers various quantization types to balance between model quality and file size, catering to different hardware requirements.

✨ Features

• Multiple Quantization Types: Offers a wide range of quantization types, from high-quality Q8_0 to extremely low-quality IQ1_S, allowing users to choose based on their hardware and performance needs.
• Specific Dataset for Quantization: All quantizations are made using the imatrix option with a dataset from here.
• Easy Download Options: Supports downloading specific files or all split files using the huggingface-cli.

📦 Installation

Prerequisites

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Downloading a Specific File

You can target the specific file you want:

huggingface-cli download bartowski/llama-3-70B-Instruct-abliterated-GGUF --include "llama-3-70B-Instruct-abliterated-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False

Downloading Split Files

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/llama-3-70B-Instruct-abliterated-GGUF --include "llama-3-70B-Instruct-abliterated-Q8_0.gguf/*" --local-dir llama-3-70B-Instruct-abliterated-Q8_0 --local-dir-use-symlinks False

You can either specify a new local-dir (llama-3-70B-Instruct-abliterated-Q8_0) or download them all in place (./)

💻 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|>

Downloading Files

The following examples show how to download different types of quantized files using the huggingface-cli:

# Download a single file
huggingface-cli download bartowski/llama-3-70B-Instruct-abliterated-GGUF --include "llama-3-70B-Instruct-abliterated-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False

# Download split files
huggingface-cli download bartowski/llama-3-70B-Instruct-abliterated-GGUF --include "llama-3-70B-Instruct-abliterated-Q8_0.gguf/*" --local-dir llama-3-70B-Instruct-abliterated-Q8_0 --local-dir-use-symlinks False

📚 Documentation

File Selection Guide

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.

Downloadable Files

📄 License

This project uses the llama3 license. For more details, please refer to the LICENSE file.

If you want to support the developer's work, you can visit the ko-fi page here.