ARIA 70B V2 GGUF

🚀 ARIA 70B V2 - GGUF

This repository provides GGUF format model files for Faradaylab's ARIA 70B V2, offering a range of quantized models for different use - cases and hardware setups.

🚀 Quick Start

To quickly get started with this model, you first need to download the appropriate GGUF file. After that, you can use it with compatible clients or libraries. For example, with llama.cpp, you can run commands like the one in the "Example llama.cpp command" section.

✨ Features

• Multiple Quantization Options: Offers a variety of quantization methods (e.g., Q2_K, Q3_K, Q4_K, etc.) to balance between model size and quality.
• Wide Compatibility: Compatible with many popular clients and libraries such as llama.cpp, text - generation - webui, KoboldCpp, etc.
• GPU Support: Many of the supported clients and libraries offer GPU acceleration, which can significantly speed up inference.

📦 Installation

Downloading GGUF Files

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text - generation - webui

Under Download Model, enter the model repo: TheBloke/ARIA - 70B - V2 - GGUF and below it, a specific filename to download, such as: aria - 70b - v2.Q4_K_M.gguf. Then click Download.

On the command line

First, install the huggingface - hub Python library:

pip3 install huggingface - hub

Then, download an individual model file to the current directory:

huggingface - cli download TheBloke/ARIA - 70B - V2 - GGUF aria - 70b - v2.Q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

You can also download multiple files at once with a pattern:

huggingface - cli download TheBloke/ARIA - 70B - V2 - GGUF --local - dir. --local - dir - use - symlinks False --include='*Q4_K*gguf'

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set the environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER = 1 huggingface - cli download TheBloke/ARIA - 70B - V2 - GGUF aria - 70b - v2.Q4_K_M.gguf --local - dir. --local - dir - use - symlinks False

Windows Command Line users: Set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER = 1 before the download command.

Joining Split Files

HF does not support uploading files larger than 50GB. So, the Q6_K and Q8_0 files are uploaded as split files.

For Q6_K

Download:

• aria - 70b - v2.Q6_K.gguf - split - a
• aria - 70b - v2.Q6_K.gguf - split - b

For Q8_0

Download:

• aria - 70b - v2.Q8_0.gguf - split - a
• aria - 70b - v2.Q8_0.gguf - split - b

To join the files: Linux and macOS:

cat aria - 70b - v2.Q6_K.gguf - split - * > aria - 70b - v2.Q6_K.gguf && rm aria - 70b - v2.Q6_K.gguf - split - *
cat aria - 70b - v2.Q8_0.gguf - split - * > aria - 70b - v2.Q8_0.gguf && rm aria - 70b - v2.Q8_0.gguf - split - *

Windows command line:

COPY /B aria - 70b - v2.Q6_K.gguf - split - a + aria - 70b - v2.Q6_K.gguf - split - b aria - 70b - v2.Q6_K.gguf
del aria - 70b - v2.Q6_K.gguf - split - a aria - 70b - v2.Q6_K.gguf - split - b

COPY /B aria - 70b - v2.Q8_0.gguf - split - a + aria - 70b - v2.Q8_0.gguf - split - b aria - 70b - v2.Q8_0.gguf
del aria - 70b - v2.Q8_0.gguf - split - a aria - 70b - v2.Q8_0.gguf - split - b

💻 Usage Examples

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 32 -m aria - 70b - v2.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n{prompt}[/INST]"

📚 Documentation

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplete list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• [text - generation - webui](https://github.com/oobabooga/text - generation - webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story - telling.
• LM Studio, an easy - to - use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• [LoLLMS Web UI](https://github.com/ParisNeo/lollms - webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy to use character - based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI - compatible AI server.
• [llama - cpp - python](https://github.com/abetlen/llama - cpp - python), a Python library with GPU accel, LangChain support, and OpenAI - compatible API server.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

• [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/ARIA - 70B - V2 - AWQ)
• [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/ARIA - 70B - V2 - GPTQ)
• [2, 3, 4, 5, 6 and 8 - bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/ARIA - 70B - V2 - GGUF)
• [Faradaylab's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Faradaylab/ARIA - 70B - V2)

Prompt template

[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
{prompt}[/INST]

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d. They are also compatible with many third - party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

Provided files

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

Q6_K and Q8_0 files are split and require joining

Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.

cat aria - 70b - v2.Q6_K.gguf - split - * > aria - 70b - v2.Q6_K.gguf && rm aria - 70b - v2.Q6_K.gguf - split - *
cat aria - 70b - v2.Q8_0.gguf - split - * > aria - 70b - v2.Q8_0.gguf && rm aria - 70b - v2.Q8_0.gguf - split - *

COPY /B aria - 70b - v2.Q6_K.gguf - split - a + aria - 70b - v2.Q6_K.gguf - split - b aria - 70b - v2.Q6_K.gguf
del aria - 70b - v2.Q6_K.gguf - split - a aria - 70b - v2.Q6_K.gguf - split - b

COPY /B aria - 70b - v2.Q8_0.gguf - split - a + aria - 70b - v2.Q8_0.gguf - split - b aria - 70b - v2.Q8_0.gguf
del aria - 70b - v2.Q8_0.gguf - split - a aria - 70b - v2.Q8_0.gguf - split - b

🔧 Technical Details

Model Information

Prompt Template

The prompt template used for this model is designed to guide the model to generate safe, unbiased, and helpful responses. It sets clear rules for the model's behavior when answering questions.

📄 License

The model is licensed under llama2.