Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These files were quantised using hardware kindly provided by Massed Compute.
This may not be a complete list; if you know of others, please let me know!
Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
Explanation of GPTQ parameters
Bits: The bit size of the quantised model.
GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.
Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)
Python code example: inference from this GPTQ model
Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
shell
1pip3 install --upgrade transformers optimum
2# If using PyTorch 2.1 + CUDA 12.x:3pip3 install --upgrade auto-gptq
4# or, if using PyTorch 2.1 + CUDA 11.x:5pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
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 special mentions: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: YeungNLP's Firefly Llama2 13B Chat
1Instruction：
2```
3夕阳西下时分，天空渐渐染上了一层橘红色。远处的山峦被映照得金光闪烁，仿佛是一幅绚烂多彩的水彩画。在山脚下的村庄里，炊烟袅袅升起，伴随着人们的欢声笑语和犬吠鸟鸣，构成一幅和谐而美好的画面。
45此时此刻，太阳已经落到了地平线以下，但它的余晖仍然洒满了大地。微风拂过树梢，带来阵阵清凉的风感；阳光透过云朵照射下来，形成一道道美丽的彩虹。在这片宁静祥和的氛围中，人们开始享受这美妙的时刻，欣赏着这片美丽的天空和大地的奇妙组合。
67当夜幕降临的时候，整个世界都变得安静了起来。月亮高高地挂在天空中，月光如水般温柔地倾泻而下，给大地带来了无限的光明与温暖。这时，你可以听到虫儿们发出的细碎的声音，感受到大自然的神奇魅力。在这个时候，你会感到自己与大自然融为一体，感受生命的真谛。
8```
910把上面的中文翻译成英文。
1112Output：
13As the sun sets in the west, the sky gradually turns a shade of orange. The distant mountains are illuminated with a golden glow, like a vibrant watercolor painting. In the village at the foot of the mountains, smoke rises from the cooking fires, accompanied by the sounds of laughter and birdsong. This creates a harmonious and beautiful scene.
1415At this moment, the sun has already set below the horizon, but its rays still illuminate the earth. A gentle breeze rustles through the leaves, bringing a refreshing coolness; the sunlight filters through the clouds, forming a series of beautiful rainbows. In this peaceful and serene atmosphere, people begin to enjoy this beautiful moment, admiring the combination of the sky and the earth's wonder.
1617As night falls, the world becomes quiet. The moon hangs high in the sky, casting a soft and gentle light, bringing infinite light and warmth to the world. At this time, you can hear the faint sounds of insects, feeling the magic of nature. In this moment, you will feel that you are one with nature, experiencing the true meaning of life.
181920Instruction:
21```
22寻寻觅觅，冷冷清清，凄凄惨惨戚戚。
23乍暖还寒时候，最难将息。
24三杯两盏淡酒，怎敌他、晚来风急！
25雁过也，正伤心，却是旧时相识。
26满地黄花堆积，憔悴损，如今有谁堪摘？
27守着窗儿，独自怎生得黑！
28梧桐更兼细雨，到黄昏、点点滴滴。
29这次第，怎一个愁字了得！
30```
3132把上面的诗词翻译成英文
3334Output:
35Wandering, cold, and lonely,
36It's hard to find a place to rest.
37Three cups of wine, two lamps,
38How can I resist the wind that's blowing?
3940The swallows are flying by,
41And it's a sad reminder of old friends.
42Yellow flowers are scattered everywhere,
43Withered and damaged, who can pick them up?
4445I'm standing by the window,
46Watching the rain fall, one drop at a time.
47This time, it's a heavy burden,
48Full of sorrow and regret.
