The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.

Here are a list of clients and libraries that are known to support GGUF:

llama.cpp.
text-generation-webui, the most widely used web UI, with many features and powerful extensions.
KoboldCpp, a fully featured web UI, with full GPU accel across multiple platforms and GPU architectures. Especially good for story telling.
LM Studio, an easy-to-use and powerful local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
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

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Compatibility

These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9

They are now also compatible with many third party UIs and libraries - please see the list at the top of the README.

Explanation of quantisation methods

Click to see details

The new methods available are:

GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
llama2-22b-gplatty.Q2_K.gguf	Q2_K	2	9.08 GB	11.58 GB	smallest, significant quality loss - not recommended for most purposes
llama2-22b-gplatty.Q3_K_S.gguf	Q3_K_S	3	9.47 GB	11.97 GB	very small, high quality loss
llama2-22b-gplatty.Q3_K_M.gguf	Q3_K_M	3	10.61 GB	13.11 GB	very small, high quality loss
llama2-22b-gplatty.Q3_K_L.gguf	Q3_K_L	3	11.61 GB	14.11 GB	small, substantial quality loss
llama2-22b-gplatty.Q4_0.gguf	Q4_0	4	12.34 GB	14.84 GB	legacy; small, very high quality loss - prefer using Q3_K_M
llama2-22b-gplatty.Q4_K_S.gguf	Q4_K_S	4	12.42 GB	14.92 GB	small, greater quality loss
llama2-22b-gplatty.Q4_K_M.gguf	Q4_K_M	4	13.18 GB	15.68 GB	medium, balanced quality - recommended
llama2-22b-gplatty.Q5_0.gguf	Q5_0	5	15.04 GB	17.54 GB	legacy; medium, balanced quality - prefer using Q4_K_M
llama2-22b-gplatty.Q5_K_S.gguf	Q5_K_S	5	15.04 GB	17.54 GB	large, low quality loss - recommended
llama2-22b-gplatty.Q5_K_M.gguf	Q5_K_M	5	15.47 GB	17.97 GB	large, very low quality loss - recommended
llama2-22b-gplatty.Q6_K.gguf	Q6_K	6	17.91 GB	20.41 GB	very large, extremely low quality loss
llama2-22b-gplatty.Q8_0.gguf	Q8_0	8	23.19 GB	25.69 GB	very large, extremely low quality loss - not recommended

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.

Example `llama.cpp` command

Make sure you are using llama.cpp from commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.

For compatibility with older versions of llama.cpp, or for any third-party libraries or clients that haven't yet updated for GGUF, please use GGML files instead.

./main -t 10 -ngl 32 -m llama2-22b-gplatty.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"

Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8. If offloading all layers to GPU, set -t 1.

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 4096 to the desired sequence length for this model. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in `text-generation-webui`

Further instructions here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model from Python using ctransformers

First install the package

bash

# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers

Simple example code to load one of these GGUF models

python

from ctransformers import AutoModelForCausalLM

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama2-22B-GPLATTY-GGUF", model_file="llama2-22b-gplatty.q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

Here's guides on using llama-cpp-python or ctransformers with LangChain:

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the chirper.ai team!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

Patreon: https://patreon.com/TheBlokeAI
Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: grimpep's Llama2 22B GPLATTY

This model is an experiment using the frankenstein script from https://huggingface.co/chargoddard/llama2-22b I merged an already merged 13B Llama v2 model GUACHAT + KIMIKO = https://huggingface.co/grimpep/13Bv2-llama-modelmerge

Then used https://huggingface.co/TheBloke/GPlatty-30B-SuperHOT-8K-fp16 as donor model.

It used 160GB of system ram to merge these models, they merge fast without swap.

No strange behaviour noticed when generating with this model (maybe more hallucinations than usual), but note that this is still all experimental.

This model might be more (didn't finetune it) "ethically" aligned than https://huggingface.co/grimpep/llama2-22b-wizard_vicuna

TheBloke/Llama2-22B-GPLATTY-GGUF

Llama2 22B GPLATTY - GGUF

Description

About GGUF